HTM Spatial Pooler
•Download as PPTX, PDF•
2 likes•2,469 views
Numenta engineer Yuwei Cui walks through how the HTM Spatial Pooler works, explaining why desired properties exist and how they work. Includes lots of graphs of SP online learning performance, discussion of topology and boosting.
Recommended
Recommended
More Related Content
What's hot
What's hot (20)
Viewers also liked
Viewers also liked (9)
Similar to HTM Spatial Pooler
Similar to HTM Spatial Pooler (20)
More from Numenta
More from Numenta (20)
Recently uploaded
Recently uploaded (20)
HTM Spatial Pooler
- 1. Yuwei Cui ycui@numenta.com HTM spatial pooler 02/8/2017
- 2. Spatial Pooler Resources • Hawkins J, Ahmad S, Dubinsky D. (2011) Cortical learning algorithm and hierarchical temporal memory. Numenta Whitepaper http://numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf • Cui Y, Ahmad S, Hawkins J (under review) The HTM Spatial Pooler: A Neocortical Algorithm for Online Sparse Distributed Coding. bioRxiv. DOI: 10.1101/085035 • HTM School: http://numenta.org/htm-school/ • Spatial Pooler in NUPIC: https://github.com/numenta/nupic/blob/master/src/nupic/research/spatial_pooler.py
- 3. Background • How do individual neurons learn to respond to specific input patterns? • How do populations of neurons represents input features? retina cochlea somatic data stream motor control millions of spike trains!
- 4. Online sequence learning with HTM HTM High Order Sequence Memory Encoder SDRData Predictions Classification Classifier Anomaly Likelihood Anomalies Spatial Pooler
- 5. HTM Spatial Pooler HTM High Order Sequence Memory Encoder SDRData Predictions Classification Classifier Anomaly Likelihood Anomalies Spatial Pooler Spatial Pooler Input 1 Input 2 Input 3 SDRs with fixed sparsity Large number of unlabeled inputs Variable sparsity ………… What properties do SP achieve?
- 6. Outline • Background • HTM spatial pooler • Properties and metrics • Simulation results
- 8. HTM spatial pooler – winner take all Overlap of the ith MC jth input Synaptic connection from jth input to ith MC
- 9. HTM spatial pooler – boosting
- 10. HTM spatial pooler – learning Hebbian Learning Rule: Active (winner) MCs reinforce their active input connections, and depress inactive inputs
- 11. Learning in HTM Spatial Pooler • Why do we need learning in SP? If inputs are random, an untrained random SP will do just as good as any trained SP However, real inputs are structured. Input SDRs occurs with non-equal probabilities. The actual inputs should be “better” represented than random inputs after learning
- 12. Properties of HTM spatial pooler • Fixed-sparseness • Distributed coding • Preserving semantic similarity • Noise robustness / Fault tolerance • Continuous learning • Stability
- 13. Properties of SP– fixed sparseness Population sparseness:
- 14. Properties of SP – distributed coding Activation prob. of the ith MC Entropy of the ith MC
- 15. Properties of SP – noise robustness
- 16. Properties of SP – continuous learning
- 17. Properties of SP – continuous learning
- 18. Properties of SP – fault tolerance Experiment 1: lesion of SP MCs We monitor: • RF center of SP MCs • Coverage of input space • Avg boost factors • Growth & elimination of synapses
- 19. Properties of SP – fault tolerance Experiment 1: lesion of SP MCs
- 20. Properties of SP – fault tolerance Experiment 1: lesion of SP MCs
- 21. Properties of SP – fault tolerance Experiment 2: lesion of afferent inputs We monitor: • RF center of SP MCs • Coverage of input space • Avg boost factors • Growth & elimination of synapses
- 22. Properties of SP – fault tolerance Experiment 2: lesion of afferent inputs
- 23. Properties of SP – fault tolerance Experiment 2: lesion of afferent inputs
- 24. Properties of HTM spatial pooler • Fixed-sparseness • Distributed coding • Preserving semantic similarity • Noise robustness / Fault tolerance • Continuous learning • Stability
- 25. Resources • Hawkins J, Ahmad S, Dubinsky D. Cortical learning algorithm and hierarchical temporal memory. In: Numenta Whitepaper [Internet]. 2011 pp. 1–68. Available: http://numenta.org/resources/HTM_CorticalLearningAlgorithms.pdf • Cui Y, Ahmad S, Hawkins J (under review) The HTM Spatial Pooler: A Neocortical Algorithm for Online Sparse Distributed Coding. bioRxiv. DOI: 10.1101/085035
- 26. Neural mechanisms of SP
Editor's Notes
- The brain is a powerful streaming analytics engine. Our brain continuously receives vast amounts of information about the external world through peripheral sensors that transform changes in light luminance, sound pressure, and skin deformations into millions of spike trains. Each cortical neuron has to make sense of a flood of time-varying inputs by forming synaptic connections to a subset of the presynaptic neurons. A central problem in neuroscience is to understand how individual cortical neurons learn to respond to specific input spike patterns, and how a population of neurons collectively represents features of the inputs in a flexible, dynamic, yet robust way.
- The current generation of HTM models continuous sequence learning in the brain.
- The HTM models a layer of cells. It consists a set of cells that are organized into MCs. The HTM neuron has three different types of inputs for each neuron. Because in the cortex cells in the same mcs have the same FF RFs, … The SP models FF The SP receives inputs from a set of input neurons. Each MC connects to a subset of the input space.
- At any time, a small set of MCs are active in the SP. These MCs are selected using WTA
- Th