SlideShare a Scribd company logo
1 of 76
Dr. Miguel Fierro
Data Scientist at Microsoft
@miguelgfierro
https://miguelgfierro.com
Intelligent Cloud GBB Ready | Lisbon Sept 2017
Deep learning solutions Deep learning tecniques
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: wikipedia
“Our strategy is to
build best-in-class
platforms and services
for an intelligent cloud
and an intelligent
edge infused with
artificial intelligence”
source: annual report 2017
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: PwC AI analysis 2017
BIGGEST
OPPORTUNITY$15.7Trillion by 2030 ~ 14% GPD
Productivity gains ($6.6T)
Automation
Increased demand ($9.1T)
Augmentation Higher quality products
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: PwC AI analysis 2017
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
DNNs (learn complex patterns
on HUGE amounts of data)
Intelligent applications … such as….
Cloud (flexibility, scalability, efficiency)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Speech
recognition
Natural Language
Processing
Computer
Vision
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
“The more data,
The better it works*”
* always read the small print
source: https://xkcd.com/1838/
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Best bet to solve intelligence
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
wait, wait, wait…
What makes deep learning deep?
input hidden output
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
input hidden hidden hidden hidden output
…
…
…
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: http://www.iro.umontreal.ca/~bengioy/yoshua_en/
“Learning multiple levels of
representation to help a learner
accomplish a task of interest,
with higher levels capturing
more abstract concepts
through a deeper composition
of computations”
Yoshua Bengio
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
low level features high level featuresmedium level features
Interesting paper about representations: https://arxiv.org/abs/1411.1792
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Convolutional Neural Networks
(CNN)
Recurrent Neural Networks
(RNN)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
MNIST with CNNs
(source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: https://www.cs.toronto.edu/~kriz/cifar.html
CIFAR with ResNet CNN
(source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Object detection with FasterRCNN
(source here)
dog
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Transfer Learning with CNNs
(source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Video classification with 3D CNNs
(source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Text classification with
CNNs (source here)
Input text: “It was a breeze to configure and worked straight away”
Books Electronics
Home &
Kitchen
Clothing Movies Health Sports
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Speech recognition
with LSTMs
(source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Time series forecasting
with LSTMs (source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Autoencoders (source here)
Original Learned
Encoder Decoder
Low dimensional
representation
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Reinforcement Learning
tutorial (basic & advanced)
source: wikipedia
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Generative Adversarial Networks (GANs)
tutorial (source here)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Diagnosis augmentation for lung cancer detection
3D CNN for nodule segmentation +
CNN for nodule classification (info1, info2)
CT scan: horizontal section of lung
Patient health monitoring with sensors (IoT):
Autoencoder on normal class +
reconstruction error abnormal class (info)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Predictive maintenance with sensors:
LSTM for classification
Visual fault detection in components:
Transfer learning with CNNs
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Generative
Asset wealth management and prediction:
Reinforcement Learning for optimal action
policy
Bots for insurance policy management:
LSTM&CNN for speech recognition+
CNN for recommendation system
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Route optimization:
Reinforcement Learning
Inventory optimization:
LSTM
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Content recommendation:
CNNs featurization + clustering
Personalized marketing:
CNN featurization + clustering
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Personalized fashion design and
production:
CNNs for image classification +
GANs for image generation
Customer demand forecasting:
LSTM
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Demand forecasting:
LSTM
Predictive maintenance:
LSTM
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Supply chain defect reduction
based on images:
Transfer learning with CNNs
On-demand production:
LSTM
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: https://github.com/Azure/fast_retraining
Degradation of accuracy
with new data
Airline delay prediction
You need to retrain!!!
Deep learning solutions Deep learning tecniques
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Learning can be viewed as finding
a and b in:
y = a.x + b
y (outputs)
x (inputs)
a,b (parameters)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
y = a.x + b
1 = a.1 + b
5 = a.5 + b
= a. + b
a=1 b=0
e = ytrue – ypred
ytrue=1
ypred depends on a,b
optimize a,b so e is
minimum
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: R. Rojas: Neural Networks, Springer-Verlag, Berlin, 1996
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Sharpening filter
Laplacian filter
Sobel x-axis filter
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Convolution Pooling PoolingConvolution
Fully
connected
Fully
connected
Input image Output
predictions
"tabby cat"
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Max pooling with 2x2 kernel and stride of 2x2
1 5 3 2
2 6 0 9
1 5 0 1
5 7 2 4
6 9
7 4
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
input hidden output
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
SoftmaxReLUtanh
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: Introduction to Natural Language Processing with FastText
Mappings of discrete objects to a high
dimensional space
bird: (1.072, 4.245, …)
dove: (1.134, 4.079, …)
woman: (-1.385, -2.104, …)
man: (-2.207, 2.118, …)
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
input
hidden
output
hidden
hidden
ti ti+1 ti+2 ti+3
…
…
…
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
number of layers
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
source: https://en.wikipedia.org/wiki/Long_short-term_memory
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
CNTK
TensorFlow
https://github.com/ilkarman/DeepLearningFrameworks: 5 frameworks, same problem
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
GIVE ME DATA!!!!
CONCEPT DRIFT IS YOUR FRIEND
MASTER THE CORE PRINCIPLES
KNOW THE FRAMEWORKS&TOOLS
Dr. Miguel Fierro
Data Scientist at Microsoft
@miguelgfierro
https://miguelgfierro.com
Intelligent Cloud GBB Ready | Lisbon Sept 2017
Intelligent Cloud GBB Ready Lisbon 2017
The code from these slides is published at:
https://github.com/ilkarman/DeepLearningFrameworks
Attribution of some images:
• http://morguefile.com
• https://unsplash.com
• Ana Corrales Photography
• http://wikipedia.org
Dataset citation:
• CIFAR-10. Learning Multiple Layers of Features from Tiny
Images, Alex Krizhevsky, 2009.
https://www.cs.toronto.edu/~kriz/cifar.html
• IMDB. https://s3.amazonaws.com/text-datasets/imdb.npz

More Related Content

Viewers also liked

Artificial Intelligence (AI) for Financial Services
Artificial Intelligence (AI) for Financial Services Artificial Intelligence (AI) for Financial Services
Artificial Intelligence (AI) for Financial Services NVIDIA
 
14 Startups Leading the Artificial Intelligence (AI) Revolution
14 Startups Leading the Artificial Intelligence (AI) Revolution14 Startups Leading the Artificial Intelligence (AI) Revolution
14 Startups Leading the Artificial Intelligence (AI) RevolutionNVIDIA
 
Transform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningTransform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningSri Ambati
 
The Spring of AI : Leveraging Collective Disruptor Insights
The Spring of AI : Leveraging Collective Disruptor InsightsThe Spring of AI : Leveraging Collective Disruptor Insights
The Spring of AI : Leveraging Collective Disruptor InsightsZinnov
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networksSi Haem
 
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習台灣資料科學年會
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceLukas Masuch
 
How to Become a Thought Leader in Your Niche
How to Become a Thought Leader in Your NicheHow to Become a Thought Leader in Your Niche
How to Become a Thought Leader in Your NicheLeslie Samuel
 

Viewers also liked (8)

Artificial Intelligence (AI) for Financial Services
Artificial Intelligence (AI) for Financial Services Artificial Intelligence (AI) for Financial Services
Artificial Intelligence (AI) for Financial Services
 
14 Startups Leading the Artificial Intelligence (AI) Revolution
14 Startups Leading the Artificial Intelligence (AI) Revolution14 Startups Leading the Artificial Intelligence (AI) Revolution
14 Startups Leading the Artificial Intelligence (AI) Revolution
 
Transform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine LearningTransform your Business with AI, Deep Learning and Machine Learning
Transform your Business with AI, Deep Learning and Machine Learning
 
The Spring of AI : Leveraging Collective Disruptor Insights
The Spring of AI : Leveraging Collective Disruptor InsightsThe Spring of AI : Leveraging Collective Disruptor Insights
The Spring of AI : Leveraging Collective Disruptor Insights
 
Deep neural networks
Deep neural networksDeep neural networks
Deep neural networks
 
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
[DSC 2016] 系列活動:李宏毅 / 一天搞懂深度學習
 
Deep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial IntelligenceDeep Learning - The Past, Present and Future of Artificial Intelligence
Deep Learning - The Past, Present and Future of Artificial Intelligence
 
How to Become a Thought Leader in Your Niche
How to Become a Thought Leader in Your NicheHow to Become a Thought Leader in Your Niche
How to Become a Thought Leader in Your Niche
 

Similar to Deep Learning for Sales Professionals

Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...
Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...
Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...Brain IoT Project
 
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...Year of the X
 
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)Comsof
 
OSMC 2018 | Monitoring Distributed Systems by Philip Griesbacher
OSMC 2018 | Monitoring Distributed Systems by Philip GriesbacherOSMC 2018 | Monitoring Distributed Systems by Philip Griesbacher
OSMC 2018 | Monitoring Distributed Systems by Philip GriesbacherNETWAYS
 
BDE: Concepts, Platform and Pilots
BDE: Concepts, Platform and PilotsBDE: Concepts, Platform and Pilots
BDE: Concepts, Platform and PilotsBigData_Europe
 
IoT Architectural Overview - 3 use case studies from InfluxData
IoT Architectural Overview - 3 use case studies from InfluxData IoT Architectural Overview - 3 use case studies from InfluxData
IoT Architectural Overview - 3 use case studies from InfluxData InfluxData
 
Leveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureLeveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureMiguel González-Fierro
 
Wolfgang Spiess–Knafl - Blockchain and social impact
Wolfgang Spiess–Knafl -  Blockchain and social impactWolfgang Spiess–Knafl -  Blockchain and social impact
Wolfgang Spiess–Knafl - Blockchain and social impactgoodbiz.
 
2nd International Conference on Big Data, IOT & NLP (BINLP 2022)
2nd International Conference on Big Data, IOT & NLP (BINLP 2022) 2nd International Conference on Big Data, IOT & NLP (BINLP 2022)
2nd International Conference on Big Data, IOT & NLP (BINLP 2022) ijcsity
 
Back to the future - Future Proof IT 2017
Back to the future - Future Proof IT 2017Back to the future - Future Proof IT 2017
Back to the future - Future Proof IT 2017Martin Hamilton
 
The BlueBRIDGE Project - Pasquale Pagano
The BlueBRIDGE Project - Pasquale PaganoThe BlueBRIDGE Project - Pasquale Pagano
The BlueBRIDGE Project - Pasquale PaganoBlue BRIDGE
 
Keynote - Fujitsu Innovation Gathering,
Keynote - Fujitsu Innovation Gathering,Keynote - Fujitsu Innovation Gathering,
Keynote - Fujitsu Innovation Gathering,Fujitsu Central Europe
 
Knowledge Graph Recommendation Systems For COVID-19
Knowledge Graph Recommendation Systems For COVID-19Knowledge Graph Recommendation Systems For COVID-19
Knowledge Graph Recommendation Systems For COVID-19Miguel González-Fierro
 
Big Data for crowd mobility
Big Data for crowd mobilityBig Data for crowd mobility
Big Data for crowd mobilitySilvia Pichler
 
Cross-Media Technologies and Applications - Future Directions for Personal In...
Cross-Media Technologies and Applications - Future Directions for Personal In...Cross-Media Technologies and Applications - Future Directions for Personal In...
Cross-Media Technologies and Applications - Future Directions for Personal In...Beat Signer
 
2017 GRESB Siemens Spring Conference
2017 GRESB Siemens Spring Conference2017 GRESB Siemens Spring Conference
2017 GRESB Siemens Spring ConferenceGRESB
 

Similar to Deep Learning for Sales Professionals (20)

Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...
Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...
Using Eclipse technologies to develop the BRAIN-IoT model-based framework for...
 
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...
Bridging the Physical and digital Adances in wearables and consumer IOT; Rani...
 
noProj.aa1.ro » M&ES4DE/DD-IT&C+A
noProj.aa1.ro  » M&ES4DE/DD-IT&C+AnoProj.aa1.ro  » M&ES4DE/DD-IT&C+A
noProj.aa1.ro » M&ES4DE/DD-IT&C+A
 
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)
FITCE Congress 2017, Madrid - Raf Meersman (CEO, Comsof)
 
OSMC 2018 | Monitoring Distributed Systems by Philip Griesbacher
OSMC 2018 | Monitoring Distributed Systems by Philip GriesbacherOSMC 2018 | Monitoring Distributed Systems by Philip Griesbacher
OSMC 2018 | Monitoring Distributed Systems by Philip Griesbacher
 
BDE: Concepts, Platform and Pilots
BDE: Concepts, Platform and PilotsBDE: Concepts, Platform and Pilots
BDE: Concepts, Platform and Pilots
 
Challenges in the Future Power Network
Challenges in the Future Power NetworkChallenges in the Future Power Network
Challenges in the Future Power Network
 
IoT Architectural Overview - 3 use case studies from InfluxData
IoT Architectural Overview - 3 use case studies from InfluxData IoT Architectural Overview - 3 use case studies from InfluxData
IoT Architectural Overview - 3 use case studies from InfluxData
 
Leveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureLeveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft Azure
 
Wolfgang Spiess–Knafl - Blockchain and social impact
Wolfgang Spiess–Knafl -  Blockchain and social impactWolfgang Spiess–Knafl -  Blockchain and social impact
Wolfgang Spiess–Knafl - Blockchain and social impact
 
BODYPASS
BODYPASSBODYPASS
BODYPASS
 
2nd International Conference on Big Data, IOT & NLP (BINLP 2022)
2nd International Conference on Big Data, IOT & NLP (BINLP 2022) 2nd International Conference on Big Data, IOT & NLP (BINLP 2022)
2nd International Conference on Big Data, IOT & NLP (BINLP 2022)
 
Back to the future - Future Proof IT 2017
Back to the future - Future Proof IT 2017Back to the future - Future Proof IT 2017
Back to the future - Future Proof IT 2017
 
Is AI generation the next platform shift?
Is AI generation the next platform shift?Is AI generation the next platform shift?
Is AI generation the next platform shift?
 
The BlueBRIDGE Project - Pasquale Pagano
The BlueBRIDGE Project - Pasquale PaganoThe BlueBRIDGE Project - Pasquale Pagano
The BlueBRIDGE Project - Pasquale Pagano
 
Keynote - Fujitsu Innovation Gathering,
Keynote - Fujitsu Innovation Gathering,Keynote - Fujitsu Innovation Gathering,
Keynote - Fujitsu Innovation Gathering,
 
Knowledge Graph Recommendation Systems For COVID-19
Knowledge Graph Recommendation Systems For COVID-19Knowledge Graph Recommendation Systems For COVID-19
Knowledge Graph Recommendation Systems For COVID-19
 
Big Data for crowd mobility
Big Data for crowd mobilityBig Data for crowd mobility
Big Data for crowd mobility
 
Cross-Media Technologies and Applications - Future Directions for Personal In...
Cross-Media Technologies and Applications - Future Directions for Personal In...Cross-Media Technologies and Applications - Future Directions for Personal In...
Cross-Media Technologies and Applications - Future Directions for Personal In...
 
2017 GRESB Siemens Spring Conference
2017 GRESB Siemens Spring Conference2017 GRESB Siemens Spring Conference
2017 GRESB Siemens Spring Conference
 

More from Miguel González-Fierro

Los retos de la inteligencia artificial en la sociedad actual
Los retos de la inteligencia artificial en la sociedad actualLos retos de la inteligencia artificial en la sociedad actual
Los retos de la inteligencia artificial en la sociedad actualMiguel González-Fierro
 
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...Miguel González-Fierro
 
Distributed training of Deep Learning Models
Distributed training of Deep Learning ModelsDistributed training of Deep Learning Models
Distributed training of Deep Learning ModelsMiguel González-Fierro
 
Running Intelligent Applications inside a Database: Deep Learning with Python...
Running Intelligent Applications inside a Database: Deep Learning with Python...Running Intelligent Applications inside a Database: Deep Learning with Python...
Running Intelligent Applications inside a Database: Deep Learning with Python...Miguel González-Fierro
 
Mastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMiguel González-Fierro
 
Speeding up machine-learning applications with the LightGBM library
Speeding up machine-learning applications with the LightGBM librarySpeeding up machine-learning applications with the LightGBM library
Speeding up machine-learning applications with the LightGBM libraryMiguel González-Fierro
 
Empowering every person on the planet to achieve more
Empowering every person on the planet to achieve moreEmpowering every person on the planet to achieve more
Empowering every person on the planet to achieve moreMiguel González-Fierro
 

More from Miguel González-Fierro (10)

Los retos de la inteligencia artificial en la sociedad actual
Los retos de la inteligencia artificial en la sociedad actualLos retos de la inteligencia artificial en la sociedad actual
Los retos de la inteligencia artificial en la sociedad actual
 
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...
Thesis dissertation: Humanoid Robot Control of Complex Postural Tasks based o...
 
Best practices in coding for beginners
Best practices in coding for beginnersBest practices in coding for beginners
Best practices in coding for beginners
 
Distributed training of Deep Learning Models
Distributed training of Deep Learning ModelsDistributed training of Deep Learning Models
Distributed training of Deep Learning Models
 
Running Intelligent Applications inside a Database: Deep Learning with Python...
Running Intelligent Applications inside a Database: Deep Learning with Python...Running Intelligent Applications inside a Database: Deep Learning with Python...
Running Intelligent Applications inside a Database: Deep Learning with Python...
 
Deep Learning for Lung Cancer Detection
Deep Learning for Lung Cancer DetectionDeep Learning for Lung Cancer Detection
Deep Learning for Lung Cancer Detection
 
Mastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep LearningMastering Computer Vision Problems with State-of-the-art Deep Learning
Mastering Computer Vision Problems with State-of-the-art Deep Learning
 
Speeding up machine-learning applications with the LightGBM library
Speeding up machine-learning applications with the LightGBM librarySpeeding up machine-learning applications with the LightGBM library
Speeding up machine-learning applications with the LightGBM library
 
Empowering every person on the planet to achieve more
Empowering every person on the planet to achieve moreEmpowering every person on the planet to achieve more
Empowering every person on the planet to achieve more
 
Deep Learning for NLP
Deep Learning for NLP Deep Learning for NLP
Deep Learning for NLP
 

Recently uploaded

Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxEmmanuel Dauda
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsappssapnasaifi408
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanMYRABACSAFRA2
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTBoston Institute of Analytics
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
MK KOMUNIKASI DATA (TI)komdat komdat.docx
MK KOMUNIKASI DATA (TI)komdat komdat.docxMK KOMUNIKASI DATA (TI)komdat komdat.docx
MK KOMUNIKASI DATA (TI)komdat komdat.docxUnduhUnggah1
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...Florian Roscheck
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfgstagge
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档208367051
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 217djon017
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxdolaknnilon
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 

Recently uploaded (20)

E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
Customer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptxCustomer Service Analytics - Make Sense of All Your Data.pptx
Customer Service Analytics - Make Sense of All Your Data.pptx
 
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /WhatsappsBeautiful Sapna Vip  Call Girls Hauz Khas 9711199012 Call /Whatsapps
Beautiful Sapna Vip Call Girls Hauz Khas 9711199012 Call /Whatsapps
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population Mean
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
MK KOMUNIKASI DATA (TI)komdat komdat.docx
MK KOMUNIKASI DATA (TI)komdat komdat.docxMK KOMUNIKASI DATA (TI)komdat komdat.docx
MK KOMUNIKASI DATA (TI)komdat komdat.docx
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...From idea to production in a day – Leveraging Azure ML and Streamlit to build...
From idea to production in a day – Leveraging Azure ML and Streamlit to build...
 
RadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdfRadioAdProWritingCinderellabyButleri.pdf
RadioAdProWritingCinderellabyButleri.pdf
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
原版1:1定制南十字星大学毕业证(SCU毕业证)#文凭成绩单#真实留信学历认证永久存档
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2
 
IMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptxIMA MSN - Medical Students Network (2).pptx
IMA MSN - Medical Students Network (2).pptx
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 

Deep Learning for Sales Professionals

  • 1. Dr. Miguel Fierro Data Scientist at Microsoft @miguelgfierro https://miguelgfierro.com Intelligent Cloud GBB Ready | Lisbon Sept 2017
  • 2. Deep learning solutions Deep learning tecniques
  • 3. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: wikipedia “Our strategy is to build best-in-class platforms and services for an intelligent cloud and an intelligent edge infused with artificial intelligence” source: annual report 2017
  • 4. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: PwC AI analysis 2017 BIGGEST OPPORTUNITY$15.7Trillion by 2030 ~ 14% GPD Productivity gains ($6.6T) Automation Increased demand ($9.1T) Augmentation Higher quality products
  • 5. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: PwC AI analysis 2017
  • 6. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro DNNs (learn complex patterns on HUGE amounts of data) Intelligent applications … such as…. Cloud (flexibility, scalability, efficiency)
  • 7. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 8. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Speech recognition Natural Language Processing Computer Vision
  • 9. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro “The more data, The better it works*” * always read the small print source: https://xkcd.com/1838/
  • 10. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Best bet to solve intelligence
  • 11. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro wait, wait, wait… What makes deep learning deep? input hidden output
  • 12. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro input hidden hidden hidden hidden output … … …
  • 13. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: http://www.iro.umontreal.ca/~bengioy/yoshua_en/ “Learning multiple levels of representation to help a learner accomplish a task of interest, with higher levels capturing more abstract concepts through a deeper composition of computations” Yoshua Bengio
  • 14. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro low level features high level featuresmedium level features Interesting paper about representations: https://arxiv.org/abs/1411.1792
  • 15. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Convolutional Neural Networks (CNN) Recurrent Neural Networks (RNN)
  • 16. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro MNIST with CNNs (source here)
  • 17. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: https://www.cs.toronto.edu/~kriz/cifar.html CIFAR with ResNet CNN (source here)
  • 18. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Object detection with FasterRCNN (source here) dog
  • 19. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Transfer Learning with CNNs (source here)
  • 20. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Video classification with 3D CNNs (source here)
  • 21. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Text classification with CNNs (source here) Input text: “It was a breeze to configure and worked straight away” Books Electronics Home & Kitchen Clothing Movies Health Sports
  • 22. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Speech recognition with LSTMs (source here)
  • 23. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Time series forecasting with LSTMs (source here)
  • 24. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Autoencoders (source here) Original Learned Encoder Decoder Low dimensional representation
  • 25. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Reinforcement Learning tutorial (basic & advanced) source: wikipedia
  • 26. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Generative Adversarial Networks (GANs) tutorial (source here)
  • 27. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Diagnosis augmentation for lung cancer detection 3D CNN for nodule segmentation + CNN for nodule classification (info1, info2) CT scan: horizontal section of lung Patient health monitoring with sensors (IoT): Autoencoder on normal class + reconstruction error abnormal class (info)
  • 28. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Predictive maintenance with sensors: LSTM for classification Visual fault detection in components: Transfer learning with CNNs
  • 29. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Generative Asset wealth management and prediction: Reinforcement Learning for optimal action policy Bots for insurance policy management: LSTM&CNN for speech recognition+ CNN for recommendation system
  • 30. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Route optimization: Reinforcement Learning Inventory optimization: LSTM
  • 31. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Content recommendation: CNNs featurization + clustering Personalized marketing: CNN featurization + clustering
  • 32. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Personalized fashion design and production: CNNs for image classification + GANs for image generation Customer demand forecasting: LSTM
  • 33. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Demand forecasting: LSTM Predictive maintenance: LSTM
  • 34. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Supply chain defect reduction based on images: Transfer learning with CNNs On-demand production: LSTM
  • 35. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: https://github.com/Azure/fast_retraining Degradation of accuracy with new data Airline delay prediction You need to retrain!!!
  • 36. Deep learning solutions Deep learning tecniques
  • 37. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Learning can be viewed as finding a and b in: y = a.x + b y (outputs) x (inputs) a,b (parameters)
  • 38. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro y = a.x + b 1 = a.1 + b 5 = a.5 + b = a. + b a=1 b=0 e = ytrue – ypred ytrue=1 ypred depends on a,b optimize a,b so e is minimum
  • 39. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: R. Rojas: Neural Networks, Springer-Verlag, Berlin, 1996
  • 40. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Sharpening filter Laplacian filter Sobel x-axis filter
  • 41. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Convolution Pooling PoolingConvolution Fully connected Fully connected Input image Output predictions "tabby cat"
  • 42. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro Max pooling with 2x2 kernel and stride of 2x2 1 5 3 2 2 6 0 9 1 5 0 1 5 7 2 4 6 9 7 4
  • 43. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro input hidden output
  • 44. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro SoftmaxReLUtanh
  • 45. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: Introduction to Natural Language Processing with FastText Mappings of discrete objects to a high dimensional space bird: (1.072, 4.245, …) dove: (1.134, 4.079, …) woman: (-1.385, -2.104, …) man: (-2.207, 2.118, …)
  • 46. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro input hidden output hidden hidden ti ti+1 ti+2 ti+3 … … …
  • 47. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro number of layers
  • 48. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro source: https://en.wikipedia.org/wiki/Long_short-term_memory
  • 49. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro CNTK TensorFlow https://github.com/ilkarman/DeepLearningFrameworks: 5 frameworks, same problem
  • 50. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 51. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 52. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 53. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 54. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 55. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 56. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 57. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 58. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 59. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 60. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 61. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 62. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 63. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 64. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 65. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 66. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 67. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 68. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 69. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 70. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 71. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 72. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 73. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro
  • 74. Intelligent Cloud GBB Ready Lisbon 2017 - Dr. Miguel Fierro @miguelgfierro GIVE ME DATA!!!! CONCEPT DRIFT IS YOUR FRIEND MASTER THE CORE PRINCIPLES KNOW THE FRAMEWORKS&TOOLS
  • 75. Dr. Miguel Fierro Data Scientist at Microsoft @miguelgfierro https://miguelgfierro.com Intelligent Cloud GBB Ready | Lisbon Sept 2017
  • 76. Intelligent Cloud GBB Ready Lisbon 2017 The code from these slides is published at: https://github.com/ilkarman/DeepLearningFrameworks Attribution of some images: • http://morguefile.com • https://unsplash.com • Ana Corrales Photography • http://wikipedia.org Dataset citation: • CIFAR-10. Learning Multiple Layers of Features from Tiny Images, Alex Krizhevsky, 2009. https://www.cs.toronto.edu/~kriz/cifar.html • IMDB. https://s3.amazonaws.com/text-datasets/imdb.npz