IT 691 Final Presentation Pace University

1
IT 691Final PresentationPace University

• Created by
• Robert M Gust
• Mark Lee Samir Hessami

2
Project Description

• Research Numenta Platform for Intelligent
  Computing (NuPIC) which attempts to harness brain
  like function to solve problems
• Brainchild of Jeff Hawkins, inventor of the Palm
  Pilot

3
Artificial Intelligence

• Two schools of thought
• Understand how the human brain works and build
  models that behave in the same way (model the
  whole brain as a single entity)
• Examine the interconnections of neurons in the
  brain and produce similar activity by leveraging
  its structure
• Picton, P. (2000). Neural Networks. Palgrave.

4
Artificial Intelligence

• Based around logic, usually in the form of a set
  of rules
• Expert Systems (medical diagnosis, game playing)
• Fuzzy logic
• Mathematical models attempt to leverage
  organization of neurons (Nodes are arranged in
  various configurations to emulate brain function)
• Neural Networks (pattern recognition)

5
Artificial Intelligence

• What is a Neural Network?
• Neural Networks are an attempt to create
  machines that work in a similar way to the human
  brain by building these machines using components
  that behave like biological neurons
• Picton, P. (2000). Neural Networks. Palgrave.

6
Examples of Neural Networks

• The perceptron is a type of artificial neural
  network invented in 1957 at the Cornell
  Aeronautical Laboratory by Frank Rosenblatt.
• The Perceptron is a single layer neural network
  whose weights and biases could be trained to
  produce a correct target vector when presented
  with the corresponding input vector.
• The training technique used is called the
  perceptron learning rule.Perceptrons are
  especially suited for simple problems in pattern
  classification.
• Vector Any device of transportation or movement
• Source http//en.wikipedia.org/wiki/

7
Examples of Neural Networks

• The best-known example of a neural network
  training algorithm is back propagation
• Backpropagation is a supervised learning
  technique used for training artificial neural
  networks. The term is an abbreviation for
  backwards propagation of errors, which requires
  that the transfer function used by the artificial
  neurons (or nodes) be differentiable.
• Source http//en.wikipedia.org/wiki/

8
Hierarchical Temporal Memory (HTM)

• Hierarchical
• Subdivide problem so it may be addressed in a
  hierarchy
• Temporal
• Include time in pattern recognition problem
• Memory
• Spatial (stored images used for comparative
  purposes in pattern recognition)

9
Numenta HTM Image Recognition

• Image is fed into network
• Static image is moved within field of view
  during learning phase and identifying phase.

10
Numenta HTM Network Level 1
Examining a single node from Level 1
Level 1 64 nodes Level 1 is a direct mapping
of the input image - As receptive field is a
4 x 4 This is unsupervised learning
11
HTM Node in Inference Mode
Level 2
The node is attempting to name the given input.
In this case the pattern is identified as the
binary 0100. Which is passed to level 2.
12
Single HTM Nodes Set of Static Images

• Step 1Spatial form sets of images using
  pixel-wise similarity. Creates a finite set of
  images for temporal analysis.

13
Single HTM Nodes Set of Sequences

• Step 2Temporal form sets of images using
  their temporal proximity to one another (is
  pattern a frequently followed by pattern b).

14
HTM Node in Inference Mode

• Spatial
• Remove Noise
• Temporal
• Capable of pooling together patterns that are
  very dissimilar from a pixel-wise perspective
• Must have a finite set of points to use

15
Numenta HTM Network Levels 1 and 2
Level 2 16 nodes Level 2 receives its Input
from the output of 4 level 1 nodes C Ds
receptive fields are 8 x 8
16
Numenta HTM Network Structure
Level 1 64 nodes Level 2 16 nodes Level 1 is
a direct mapping of the input image - As
receptive field is a 4 x 4 Level 2 receives
its Input from the output Of 4 level 1 nodes C
Ds receptive fields are 8 x 8 Level 3 - the
invariant form (label / name)
George, D Jaros, B. (2007). The HTM Learning
Algorithms. Numenta.
17
Prediction

• What is prediction?
• Statistically based assumption
• Neuroanatomists have known for a long time that
  the brain is saturated with feedback connections.
  For example, in the circuit between the
  neocortex and a lower structure called the
  thalamus, connections going backward (toward the
  input) exceed the connections going forward by
  almost a factor of ten! That is, for every fiber
  feeding information forward into the neocortex,
  there are ten fibers feeding information back
  toward the senses.
• Hawkins, (2004) On Intelligence, 25

18
Further Research

• Not just for image recognition
• Unsupervised learning opens up the possibility
  for determining causality for novel problems
• Hawkins Weather pattern example