What the Brain says about Machine Intelligence
•
15 gefällt mir•11,549 views
This document discusses machine intelligence and the cortical theory of intelligence. It begins by comparing approaches to computing in the 1940s-1950s and 2010s-2020s, noting that while many approaches existed, one dominant paradigm eventually emerged in both eras due to flexibility and scalability. It then outlines Numenta's cortical theory, including hierarchical temporal memory (HTM), and how HTM models the neocortex. The document details Numenta's research applying HTM to areas like anomaly detection, language processing, and vision. It argues HTM may be the dominant machine intelligence paradigm due to the neocortex's success and HTM's ability to model the neocortex's common algorithms across modalities.
Empfohlen
Empfohlen
Weitere ähnliche Inhalte
Was ist angesagt?
Was ist angesagt? (20)
Andere mochten auch
Andere mochten auch (8)
Ähnlich wie What the Brain says about Machine Intelligence
Ähnlich wie What the Brain says about Machine Intelligence (20)
Mehr von Numenta
Mehr von Numenta (20)
Kürzlich hochgeladen
Kürzlich hochgeladen (20)
What the Brain says about Machine Intelligence
- 1. November 21, 2014 Jeff Hawkins jhawkins@Numenta.com What the Brain Says About Machine Intelligence
- 2. 1940’s 1950’s - Dedicated vs. universal - Analog vs. digital - Decimal vs. binary - Wired vs. memory-based programming - Serial vs. random access memory Many approaches - Universal - Digital - Binary - Memory-based programming - Two tier memory One dominant paradigm The Birth of Programmable Computing Why Did One Paradigm Win? - Network effects Why Did This Paradigm Win? - Most flexible - Most scalable
- 3. 2010’s 2020’s The Birth of Machine Intelligence - Specific vs. universal algorithms - Mathematical vs. memory-based - Batch vs. on-line learning - Labeled vs. behavior-based learning Many approaches - Universal algorithms - Memory-based - On-line learning - Behavior-based learning One dominant paradigm Why Will One Paradigm Win? - Network effects Why Will This Paradigm Win? - Most flexible - Most scalable How Do We Know This is Going to Happen? - Brain is proof case - We have made great progress
- 4. 1) Discover operating principles of neocortex. 2) Create machine intelligence technology based on neocortical principles. Numenta’s Mission Talk Topics - Cortical facts - Cortical theory - Research roadmap - Applications - Thoughts on Machine Intelligence
- 5. What the Cortex Does patterns Learns a model of world from changing sensory data The model generates - predictions - anomalies - actions Most sensory changes are due to your own movement The neocortex learns a sensory-motor model of the world patterns patterns light sound touch retina cochlear somatic
- 6. Cortical Facts Hierarchy Cellular layers Mini-columns Neurons: 3-10K synapses - 10% proximal - 90% distal Active dendrites Learning = new synapses Remarkably uniform - anatomically - functionally 2.5 mm Sheet of cells 2/3 4 6 5
- 7. Cortical Theory Hierarchy Cellular layers Mini-columns Neurons: 3-10K synapses - 10% proximal - 90% distal Active dendrites Learning = new synapses Remarkably uniform - anatomically - functionally Sheet of cellsHTM Hierarchical Temporal Memory 1) Hierarchy of identical regions 2) Each region learns sequences 3) Stability increases going up hierarchy if input is predictable 4) Sequences unfold going down Questions - What does a region do? - What do the cellular layers do? - How do neurons implement this? - How does this work in hierarchy? 2/3 4 6 5
- 8. 2/3 4 5 6 Cellular Layers Sequence memory: Sequence memory: Sequence memory: Sequence memory: Inference (high-order) Inference (sensory-motor) Motor Attention FeedforwardFeedback Each layer is a variation of common sequence memory algorithm. These are universal functions. They apply to: - all cortical regions - all sensory-motor modalities. Copy of motor commands Sensor data Higher region Sub-cortical Motor centers Lower region
- 9. 2/3 4 5 6 Sequence memory: Sequence memory: Sequence memory: Sequence memory: ? ? ? ? How Does Sequence Memory Work?
- 10. HTM Temporal Memory Learns sequences Recognizes and recalls sequences Predicts next inputs - High capacity - Distributed - Local learning rules - Fault tolerant - No sensitive parameters - Generalizes
- 11. HTM Temporal Memory Not Just Another ANN 1) Cortical Anatomy Mini-columns Inhibitory cells Cell connectivity patterns 2) Sparse Distributed Representations 3) Realistic Neurons Active dendrites Thousands of synapses Learn via synapse formation numenta.com/learn/
- 12. 2/3 4 5 6 Research Roadmap Sensory-motor Inference High-order Inference Motor Sequences Attention/Feedback Theory 98% Extensively tested Commercial Theory 80% In development Theory 50% Theory 30% Streaming Data Capabilities: Prediction Anomaly detection Classification Applications: Predictive maintenance Security Natural Language Processing
- 13. HTM Encoder SDRData stream Predictions Anomalies Classification Streaming Data Applications Numbers Categories Date Time GPS Words Applications Servers Biometrics Medical Vehicles Industrial equipment Social media Comm. networks
- 14. Streaming Data Applications Server metrics Human metrics Natural languageGPS dataEEG data Financial data
- 15. . . . Anomaly Detection in Server Metrics (Grok for AWS) HTM Encoder SDRServer Metric Anomaly Score HTM Encoder SDRServer Metric Anomaly Score Mobile Dashboard Servers sorted by anomaly score Continuously updated Web Dashboard
- 16. What Kind of Anomalies Can HTM Detect? Sudden changes Slow changes Changes in noisy dataSubtle changes in regular data
- 17. Changes that humans can’t see Engineer manually started build on automated build server What Kind of Anomalies Can HTM Detect?
- 18. Created large Zip file Anomaly Detection in Human Metrics Keystrokes File access CPU usage App access
- 19. Anomaly Detection in Financial and Social Media Data Stock volume Social media Stock volume Social media
- 20. Berkeley Cognitive Technology Group Classification of EEG Data
- 22. Document corpus (e.g. Wikipedia) 128 x 128 100K “Word SDRs” - = Apple Fruit Computer Macintosh Microsoft Mac Linux Operating system …. Natural Language
- 23. Training set frog eats flies cow eats grain elephant eats leaves goat eats grass wolf eats rabbit cat likes ball elephant likes water sheep eats grass cat eats salmon wolf eats mice lion eats cow dog likes sleep elephant likes water cat likes ball coyote eats rodent coyote eats rabbit wolf eats squirrel dog likes sleep cat likes ball ---- ---- ----- Word 3Word 2Word 1 Sequences of Word SDRs HTM
- 24. Training set eats“fox” ? frog eats flies cow eats grain elephant eats leaves goat eats grass wolf eats rabbit cat likes ball elephant likes water sheep eats grass cat eats salmon wolf eats mice lion eats cow dog likes sleep elephant likes water cat likes ball coyote eats rodent coyote eats rabbit wolf eats squirrel dog likes sleep cat likes ball ---- ---- ----- Sequences of Word SDRs HTM
- 25. Training set eats“fox” rodent - Learning is unsupervised - Semantic generalization - Works across languages - Many applications Intelligent search Sentiment analysis Semantic filtering frog eats flies cow eats grain elephant eats leaves goat eats grass wolf eats rabbit cat likes ball elephant likes water sheep eats grass cat eats salmon wolf eats mice lion eats cow dog likes sleep elephant likes water cat likes ball coyote eats rodent coyote eats rabbit wolf eats squirrel dog likes sleep cat likes ball ---- ---- ----- Sequences of Word SDRs HTM
- 26. Server metrics Human metrics Natural language GPS dataEEG dataFinancial data All these applications run on the exact same HTM code.
- 27. 2/3 4 5 6 Research Roadmap Sensory-motor Inference High-order Inference Motor Sequences Attention/Feedback Theory 98% Extensively tested Commercial Theory 80% In development Theory 50% Theory 30% Streaming Data Capabilities: Prediction Anomaly detection Classification Applications: IT Security Natural Language Processing Static Data (via active learning) Capabilities: Classification Prediction Applications: Vision image classification Network classification Classification of connected graphs
- 28. 2/3 4 5 6 Research Roadmap Sensory-motor Inference High-order Inference Motor Sequences Attention/Feedback Theory 98% Extensively tested Commercial Theory 80% In development Theory 50% Theory 30% Streaming Data Capabilities: Prediction Anomaly detection Classification Applications: IT Security Natural Language Processing Static Data (via active learning) Capabilities: Classification Prediction Applications: Vision image classification Network classification Classification of connected graphs Static and/or streaming Data Capabilities: Goal-oriented behavior Applications: Robotics Smart bots Proactive defense
- 29. 2/3 4 5 6 Research Roadmap Sensory-motor Inference High-order Inference Motor Sequences Attention/Feedback Theory 98% Extensively tested Commercial Theory 80% In development Theory 50% Theory 30% Streaming Data Capabilities: Prediction Anomaly detection Classification Applications: IT Security Natural Language Processing Static Data (via active learning) Capabilities: Classification Prediction Applications: Vision image classification Network classification Classification of connected graphs Static and/or streaming Data Capabilities: Goal-oriented behavior Applications: Robotics Smart bots Proactive defense Enables : Multi-sensory modalities Multi-behavioral modalities
- 30. - Algorithms are documented - Multiple independent implementations NuPIC www.Numenta.org - Numenta’s software is open source (GPLv3) - Numenta’s daily research code is online - Active discussion groups for theory and implementation - Collaborative IBM Almaden Research, San Jose, CA DARPA, Washington D.C Cortical.IO, Austria Research Transparency
- 31. NuPIC Community
- 32. Machine Intelligence Landscape Cortical (e.g. HTM) ANNs (e.g. Deep learning) A.I. (e.g. Watson)
- 33. Machine Intelligence Landscape Premise Biological Mathematical Engineered Cortical (e.g. HTM) ANNs (e.g. Deep learning) A.I. (e.g. Watson)
- 34. Machine Intelligence Landscape Premise Biological Mathematical Engineered Data Spatial-temporal Language, Behavior Spatial-temporal Language Documents Cortical (e.g. HTM) ANNs (e.g. Deep learning) A.I. (e.g. Watson)
- 35. Machine Intelligence Landscape Premise Biological Mathematical Engineered Data Spatial-temporal Language, Behavior Spatial-temporal Language Documents Capabilities Classification Prediction Goal-oriented Behavior Classification NL Query Cortical (e.g. HTM) ANNs (e.g. Deep learning) A.I. (e.g. Watson)
- 36. Machine Intelligence Landscape Premise Biological Mathematical Engineered Data Spatial-temporal Language, Behavior Spatial-temporal Language Documents Capabilities Classification Prediction Goal-oriented Behavior Classification NL Query Path to M.I.? Yes Probably not Probably not Cortical (e.g. HTM) ANNs (e.g. Deep learning) A.I. (e.g. Watson)
- 40. Geospatial Anomalies Deviation in path Change in direction
- 42. Time = 1 Learning Transitions
- 43. Time = 2 Learning Transitions
- 44. Learning Transitions Form connections to previously active cells. Predict future activity.
- 45. - This is a first order sequence memory. - It cannot learn A-B-C-D vs. X-B-C-Y. - Mini-columns turn this into a high-order sequence memory. Learning Transitions Multiple predictions can occur at once. A-B A-C A-D
- 46. Forming High Order Representations Feedforward: Sparse activation of columns Burst of activity Highly sparse unique pattern Unpredicted Predicted Feedforward: Sparse activation of columns
- 47. Representing High-order Sequences A X B B C C Y D Before training A X B’’ B’ C’’ C’ Y’’ D’ After training Same columns, but only one cell active per column. IF 40 active columns, 10 cells per column THEN 1040 ways to represent the same input in different contexts
- 48. SDR Properties subsampling is OK 3) Union membership: Indices 1 2 | 10 Is this SDR a member? 2) Store and Compare: store indices of active bits Indices 1 2 3 4 5 | 40 1) 2) 3) …. 10) 2% 20%Union 1) Similarity: shared bits = semantic similarity
- 49. What Can Be Done With Software 1 layer 30 msec / learning-inference-prediction step 10-6 of human cortex 2048 columns 65,000 neurons 300M synapses
- 50. Challenges Dendritic regions Active dendrites 1,000s of synapses 10,000s of potential synapses Continuous learning Challenges and Opportunities for Neuromorphic HW Opportunities Low precision memory (synapses) Fault tolerant - memory - connectivity - neurons - natural recovery Simple activation states (no spikes) Connectivity - very sparse, topological
- 51. 2/3 4 5 6 Cellular Layers Sequence memory Sequence memory Sequence memory Sequence memory Inference Inference Motor Attention FeedforwardFeedback Each layer implements a variation of a common sequence memory algorithm. Higher cortexSensor/lower cortex Lower cortex Motor center
- 52. Why Will Machine Intelligence be Based on Cortical Principles? 1) Cortex uses a common learning algorithm vision hearing touch behavior 2) Cortical algorithm is incredibly adaptable languages engineering science arts … 3) Network effects Hardware and software efforts will focus on most universal solution
- 53. 2/3 4 5 6 Cellular Layers Sequence memory: Sequence memory: Sequence memory: Sequence memory: Inference Inference Motor Attention FeedforwardFeedback Each layer is a variation of a common sequence memory algorithm. Higher cortexSensor/lower cortex Lower cortex Sub-cortical motor center Inputs/outputs define the role of each layer.
- 56. Sparse Distributed Representations (SDRs) - Sensory perception - Planning - Motor control - Prediction - Attention Sparse Distribution Representations are used everywhere in the cortex.
- 57. Sparse Distributed Representations What are they • Many bits (thousands) • Few 1’s mostly 0’s • Example: 2,000 bits, 2% active • Each bit has semantic meaning • No bit is essential 01000000000000000001000000000000000000000000000000000010000…………01000 Desirable attributes • High capacity • Robust to noise and deletion • Efficient and fast • Enable new operations
- 58. SDR Operations 1) Similarity: shared bits = semantic similarity subsampling is OK 3) Union membership: Indices 1 2 | 10 Is this SDR a member? 2) Store and Compare: store indices of active bits Indices 1 2 3 4 5 | 40 1) 2) 3) …. 10) 2% 20%Union
- 59. SmartHarbors
- 60. GPS to SDR Encoder
- 61. GPS to SDR Encoder
- 62. GPS to SDR Encoder
- 63. GPS to SDR Encoder
- 64. Feedback Local Feedforward Activates cell Neurons Biological neuron HTM neuron Non-linear Dendritic AP’s Depolarize soma Coincidence detectors HTM SynapsesBiological Synapses Learning is formation of new synapses. Synapses have low fidelity. Connection weight is binary 0.0 1.00.4 Learning forms new connections (“permanence” is scalar) 0 1 Feedforward Activates cell Prediction: Recognize hundreds of unique patterns Synapses Activation: Recognize dozens of unique patterns
- 65. SDRs are used everywhere in the cortex. Sparse Distributed Representations (SDRs)
- 66. From: Prof. Hasan, Max-Planck- Institute for Research
- 67. x = 0100000000000000000100000000000110000000 • Extremely high capacity • Robust to noise and deletions • Have many desirable properties • Solve semantic representation problem Attributes SDR Basics • Large number of neurons • Few active at once • Every cell represents something • Information is distributed • SDRs are binary 10 to 15 synapses are sufficient to recognize patterns in thousands of cells. A single dendrite can recognize multiple unique patterns without confusion.
- 68. Example: SDR Classification Capacity in Presence of Noise • n = number of bits in SDR • w = number of 1 bits • W = number of vectors that overlap vector x by b bits • Probability of false positive for one stored pattern • Probability of false positive for M stored patterns Wx (n,w,b) = wx b æ èç ö ø÷ ´ n - wx w - b æ èç ö ø÷ fpw n (q) = Wx (n,w,b) b=q w å n w æ èç ö ø÷ fpX (q) £ fpwxi n (q) i=0 M-1 å n = 2048, w = 40 With 50% noise, you can classify 1015 patterns with an error < 10-11 n = 64, w=12 With 33% noise, you can classify only 10 patterns with an error 0.04% Link.to.whitepaper.com