Hierarchical Temporal Memory
Surya Prakash Pathak
Data Scientist, Red Hat
1
Anomaly Detection
Machine Learning at SLAC
Agenda
HTM-Anomaly Detection
2
CONFIDENTIAL Designator
A Thought Experiment
HTM-Anomaly Detection
3
CONFIDENTIAL Designator
A Thought Experiment
HTM-Anomaly Detection
4
Spatial
Temporal
CONFIDENTIAL Designator
Deep Neural Networks
HTM-Anomaly Detection
5
CONFIDENTIAL Designator
HTM
HTM-Anomaly Detection
6
CONFIDENTIAL Designator
History
HTM-Anomaly Detection
7
CONFIDENTIAL Designator
Neocortex
HTM-Anomaly Detection
8
CONFIDENTIAL Designator
Neocortex Structure
HTM-Anomaly Detection
9
CONFIDENTIAL Designator
Cortical Column
HTM-Anomaly Detection
10
CONFIDENTIAL Designator
Deep Neural Net Neuron
HTM-Anomaly Detection
11
CONFIDENTIAL Designator
Real Neuron
HTM-Anomaly Detection
12
Dendrite
Axon
Dendrites
CONFIDENTIAL Designator
HTM Neuron
HTM-Anomaly Detection
13
CONFIDENTIAL Designator
Neural Learning
HTM-Anomaly Detection
14
-> BIology
-> HTM - Synapse “permanence” (Synapse state)
CONFIDENTIAL Designator
HTM Cortical Column
HTM-Anomaly Detection
15
CONFIDENTIAL Designator
Sparse Distributed Representations
HTM-Anomaly Detection
16
Capacity :
Fixed sparseness
CONFIDENTIAL Designator
Sequence (formally Temporal) Memory
HTM-Anomaly Detection
17
CONFIDENTIAL Designator
High Order Sequence Prediction
HTM-Anomaly Detection
18
CONFIDENTIAL Designator
Sequence Prediction Step by Step
HTM-Anomaly Detection
19
Trained Two Sequences A-B-C-D and X-B-C-Y
CONFIDENTIAL Designator
Anomaly
HTM-Anomaly Detection
20
CONFIDENTIAL Designator
HTM- Anomaly Detection
HTM-Anomaly Detection
21
CONFIDENTIAL Designator
HTM- Anomaly Detection
HTM-Anomaly Detection
22
Raw Anomaly Scores
Raw anomaly scores is the fraction of active columns that were not predicted.
Set of cells predicted from previous timestamp
Current set of active cells
Number of active columns
0 : Perfectly predicted
1 : Completely unpredicted
CONFIDENTIAL Designator
HTM- Anomaly Detection
HTM-Anomaly Detection
23
Raw Anomaly Scores
CONFIDENTIAL Designator
HTM- Anomaly Detection
HTM-Anomaly Detection
24
Anomaly Likelihood: Likelihood that a given anomaly score represents a true Anomaly
Compute normal distribution over history
Anomaly Likelihood is computed as the complement of the tail probability
Mean of all anomaly scores so far
Mean of all anomaly scores in recent time window (10 samples)
CONFIDENTIAL Designator
HTM- Anomaly Detection
HTM-Anomaly Detection
25
Anomaly Likelihood
CONFIDENTIAL Designator
Anomaly Detection Operate first CPU-usage data
HTM-Anomaly Detection
26
How data is extracted?
CONFIDENTIAL Designator
Anomaly Detection using HTM
HTM-Anomaly Detection
27
Demo - Run through the notebook showing the time series data for input signal, prediction and detection of anomalies.
CONFIDENTIAL Designator
Commercials applications HTM
HTM-Anomaly Detection
28
https://grokstream.com/
https://www.cortical.io/
https://intelletic.com/
CONFIDENTIAL Designator
Acknowledgements
HTM-Anomaly Detection
29
https://github.com/htm-community/htm.core
https://numenta.com/
CONFIDENTIAL Designator
30
Who am I?
CONFIDENTIAL Designator