Brains, Data, and Machine Intelligence (2014 04 14 London Meetup)

ResearchNeocortical theory Algorithms

NuPICOpen source community

ProductsAutomated streaming analytics

Catalyst for machine intelligence

Brains, Data, and Machine Intelligence

Jeff [email protected]

“If you invent a breakthrough so computers can learn, that is worth 10 Microsofts”

"If you invent a breakthrough so computers that learn that is worth 10 Micros

1) What principles will we use to build intelligent machines?

2) What applications will drive adoption in the near and long term?

Machine Intelligence

1) Flexible (universal learning machine)

2) Robust

3) If we knew how the neocortex worked, we would be in a race to build them.

Machine intelligence will be built on the principles of the neocortex

What the Cortex Does

data streamretina

cochlea

somatic

The neocortex learns a model from sensory data

- predictions - anomalies - actions

The neocortex learns a sensory-motor model of the world

“Hierarchical Temporal Memory” (HTM)

1) Hierarchy of nearly identical regions

- across species- across modalities

retina

cochlea

somatic2) Regions are mostly sequence memory

- for inference- for motor

3) Feedforward: Temporal stability

Feedback: Unfold sequences

data stream

2.5 mm

Cortex

Layers

Layers & Columns

2/3456

2/3

4

5

6

Sequence memory: high-order inference

Sequence memory: sensory-motor inference

Sequence memory: motor generation

Sequence memory: attention

Cortical Learning Algorithm (CLA)

CLA is a cortical model, not another “neural network”

2/3

4

5

6

L4 and L2/3: Feedforward Inference

Copy of motor commands

Sensor/afferent data

Learns sensory-motor transitions

Learns high-order transitions Stable

Predicted

Pass throughchanges

Un-predicted

Layer 4 learns sensory-motor transitions.Layer 3 learns high-order transitions.

These are universal inference steps.They apply to all sensory modalities.

Next higher region

A-B-C-DX-B-C-Y

A-B-C- ? DX-B-C- ? Y

2/3

4

5

6

L5 and L6: Feedback, Behavior and Attention

Learns sensory-motor transitions

Learns high-order transitions

Well understoodtested / commercial

Recalls motor sequences

Attention

90% understoodtesting in progress

50% understood

10% understood

Feed

forw

ard

Feed

bac

k

How does a layer of neurons learn sequences?

2/3

4

5

6

Learns high-order transitions

First:- Sparse Distributed Representations- Neurons

Cortical Learning Algorithm (CLA)

Sparse Distributed Representations (SDRs) • Many bits (thousands)

• Few 1’s mostly 0’s• Example: 2,000 bits, 2% active

• Each bit has semantic meaningLearned

01000000000000000001000000000000000000000000000000000010000…………01000

Dense Representations• Few bits (8 to 128)• All combinations of 1’s and 0’s• Example: 8 bit ASCII

• Bits have no inherent meaningArbitrarily assigned by programmer

01101101 = m

SDR Properties

1) Similarity: shared bits = semantic similarity

subsampling is OK

3) Union membership:

Indices12|10

Is this SDRa member?

2) Store and Compare: store indices of active bits

Indices12345|40

1)2)3)

….10)

2%

20%Union

Model neuronFeedforward

100’s of synapses“Classic” receptive fieldContext

1,000’s of synapsesDepolarize neuron“Predicted state”

Active Dendrites

Pattern detectorsEach cell can recognize100’s of unique patterns

Neurons

Learning TransitionsFeedforward activation

Learning TransitionsInhibition

Learning TransitionsSparse cell activation

Time = 1Learning Transitions

Time = 2Learning Transitions

Learning TransitionsForm connections to previously active cells.Predict future activity.

This is a first order sequence memory.It cannot learn A-B-C-D vs. X-B-C-Y.

Learning TransitionsMultiple predictions can occur at once.A-B A-C A-D

High-order Sequences Require Mini-columnsA-B-C-D vs. X-B-C-Y

A

X B

B

C

C

Y

D

Before trainingA

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 columnTHEN 1040 ways to represent the same input in different contexts

Cortical Learning Algorithm (CLA)aka Cellular Layer

Converts input to sparse representations in columnsLearns transitionsMakes predictions and detects anomalies

Applications1) High-order sequence inference L2/32) Sensory-motor inference L43) Motor sequence recall L5

Capabilities- On-line learning- High capacity- Simple local learning rules- Fault tolerant- No sensitive parameters

Basic building block of neocortex/machine intelligence

Anomaly Detection Using CLA

CLA

Encoder

SDR Prediction errorTime averageHistorical comparison

Metric + Time Anomaly

score

CLA

Encoder

SDR Prediction errorTime averageHistorical comparison

Metric + Time Anomaly

score

.

.

.

CloudWatch

AWS

Grok for AWS Users

- Automated model creation via web, CLI, API

- Breakthrough anomaly detection

- Dramatically reduces false positives/negatives

- Supports auto-scaling and custom metrics

CustomerInstances & Services

- Mobile client

- Instant status check

- Mobile OS and email alerts

- Drill down to determine severity

Grok for AWS Mobile UI

Sorted by anomaly score Continuously updated Continuously learning

What Can the CLA/Grok Detect?

Sudden changes

Slow changes Subtle changes in regular data

What Can the CLA/Grok Detect?

Patterns that humans can’t seeChanges in noisy data

CEPT.at - Natural Language Processing Using SDRs and CLA

Document corpus(e.g. Wikipedia)

128 x 128

100K “Word SDRs”

- =Apple Fruit Computer

MacintoshMicrosoftMacLinuxOperating system….

Sequences of Word SDRs

Training setfrog eats fliescow eats grainelephant eats leavesgoat eats grasswolf eats rabbitcat likes ballelephant likes watersheep eats grasscat eats salmonwolf eats micelion eats cowdog likes sleepelephant likes watercat likes ballcoyote eats rodentcoyote eats rabbitwolf eats squirreldog likes sleepcat likes ball---- ---- -----

Word 3Word 2Word 1

Sequences of Word SDRs

Training set

eats“fox”

?

frog eats fliescow eats grainelephant eats leavesgoat eats grasswolf eats rabbitcat likes ballelephant likes watersheep eats grasscat eats salmonwolf eats micelion eats cowdog likes sleepelephant likes watercat likes ballcoyote eats rodentcoyote eats rabbitwolf eats squirreldog likes sleepcat likes ball---- ---- -----

Sequences of Word SDRs

Training set

eats“fox”

rodent

1)Word SDRs created without supervision

2)Semantic generalizationSDR: lexicalCLA: grammatic

3)Commercial applicationsSentiment analysisAbstractionImproved text to speechDialog, Reporting, etc.www.Cept.at

frog eats fliescow eats grainelephant eats leavesgoat eats grasswolf eats rabbitcat likes ballelephant likes watersheep eats grasscat eats salmonwolf eats micelion eats cowdog likes sleepelephant likes watercat likes ballcoyote eats rodentcoyote eats rabbitwolf eats squirreldog likes sleepcat likes ball---- ---- -----

Cept and Grok use exact same code base

eats“fox”

rodent

Source code for:- Cortical Learning Algorithm- Encoders- Support libraries

Single source tree (used by GROK), GPLv3

Active and growing community

Hackathons

Education Resources

www.Numenta.org

NuPIC Open Source Project

Research- Implement and test L4 sensory/motor inference- Introduce hierarchy (?)- Publish

NuPIC- Grow open source community- Support partners, e.g. IBM, CEPT

Grok- Create commercial value for CLA

Attract resourcesProvide a “target” and market for HW

- Explore new application areas

Goals For 2014

1) The neocortex is as close to a universal learning machine as we can imagine

2) Machine intelligence will be built on the principles of the neocortex

3) HTM is an overall theory of neocortex

4) CLA is a building block

5) Near term applicationsanomaly detection, prediction, NLP

6) Participate www.numenta.org

Future of Machine Intelligence

Future of Machine Intelligence

Definite- Faster, Bigger- Super senses- Fluid robotics- Distributed

hierarchyMaybe- Humanoid robots- Computer/Brain

interfaces for all

Not- Uploaded brains- Evil robots

Why Create Intelligent Machines?

Thank You

Live better Learn more