A brief history of Neural Networks

Faisal Qureshi
http://www.vclab.ca

  • Claude Shannon, Father of Information Theory.

    I visualise a time when we will be to robots what dogs are to humans, and I’m rooting for the machines.

  • Jeff Hawkins, Founder of Palm Computing.

The key to artificial intelligence has always been the representation.

Lesson Plan

  • Computational models of Neurons
  • Pre-deep learning
  • Imagenet 2012
  • Takeaways
    • What
    • How
    • Why now?
    • Impact
  • Ethical and social implications

McCulloch and Pitts (1943)

  • Proposed a model of nervous systems as a network of threshold units.
  • Connections between simple units performing elementry operations give rise to intelligence.

Threshold units

  • Neuron (picture from Wikipedia)
  • Artificial neuron

Learning via reinforcing connections between Neurons (1949 to 1982)

Hebbian Learning

  • Hebbian Learning (Donald Hebb, 1949) principle proposes to learn patterns by reinforcing connections between Neurons that tend to fire together.
    • Biologically plausible, but it is not used in practice
  • First artificial neural network consisting of 40 neurons (Marvin Minsky, 1951)
    • Uses Hebbian Learning

Perceptron

  • Frank Rosenblatt (1958) perceptron to classify 20x20 images
    • Percpetron is neural network comprising a single neuron

Cat visual cortex

  • David Hubel and Torsten Wiesel studied cat visual cortex and showed that visual information goes through a series of processing steps: 1) edge detection; 2) edge combination; 3) motion perception; etc. (Hubeland Wiesel, 1959)

Backpropatation

  • Backpropagation for artificial neural networks (Paul Werbos, 1982)
    • An application of chain-rule from differential calculus

Towards (deep) neural networks

Neocognitron

  • Fukushima (1980) implemented Neocognitnron that was capable of handwritten character recognition.
    • This model was based upon the findings of Hubel and Wiesel.
    • This model can be seen as a precursor of modern convolutional networks.

Hidden units and backpropagation

  • Rumelhart et al. (1988) used backpropagation to train a network similar to Neocognitron.
    • Units in hidden layers learn meaningful representations

LeNet

  • In 1989, LeCun et al. proposed LeNet, a convolution neural network very similar to networks that we see today
    • Capable for recognizing hand-written digits
    • Trained using backpropagation

Deep learning (the beginning)

ImageNet Large Scale Visual Recognition Challenge

  • Large amount of training data is critical to the success of deep learning methods
  • ImageNet challenge was devised to capture the performance of various image recognition methods
    • 1 million images belonging to 1000 different classes
    • It's size was key to the development early deep learning models

Datasets

  • Datasets used for deep learning model develop are divided into three sets:
    • Training set is used train the deep learning model;
    • Validation set is used to tune the hyperparameters, implement early stopping, etc.; and
    • Test set is used to evaluate model performance.

AlexNet (2012)

  • Krizhevsky et al. trained a convolution network, similar to LeNet5, but containing far more layers, neurons, and connections, on the ImageNet Challenge using Graphical Processing Units (GPUs). This model was able to beat the state-of-the-art image classification methods by a large margin.
  • GPUs are criticial to the success of deep learning methods.
  • Models may outperform humans!?

Deep learning takes over (2012 onwards)

  • Large datasets and vast GPU compute infrastructures led to larger and more complex deep learning models for solving problems in a variety of domains ranging
    • from computer vision to speach recognition,
    • from medical imaging to text understanding,
    • from computer graphics to industrial design,
    • from autonomous driving to drug discovery, etc.

Takeaways

What

  • Deep learning is a natural extension of artificial neural networks of the 90s.
    • Extracts useful patterns from data
    • Learns powerful representations
    • Reduces the "semantic gap"

How

  • Chain rule (or backpropagation)
    • Computes how error (or more generally, the quantity to optimize) changes when model parameters change
  • Stochastic gradient descent
    • Iteratively update network parameters to "minimize the error" (How)
  • Convolutions
    • Bakes in the intuition that signal is structured and often has some stationary properties
    • Allows processing of large signals
  • Hidden layers

Why now?

  • GPUs that support vectorized processing (tensor operations)
  • Large datasets

Engineering advances

  • Computationally speaking, a deep learning model can be formalized as a graph of tensor operations:
    • Nodes perform tensor operations; and
    • Results propagate along edges between nodes.
  • Provides new ways of thinking about deep learning models.
    • Recursive nature: each node is capable of sophisticated, non-trivial computation, perhaps leveraging another neural network
  • Autodiff
    • Techniques to evaluate the "derivative of a computer program"
  • Deep learning frameworks
    • PyTorch
    • TensorFlow
    • etc.

Impact

  • Image classification
  • Face recognition
  • Speech recognition
  • Text-to-speech generation
  • Handwriting transcription
  • Medical image analysis and diagnosis
  • Ads
  • Cars: lane-keeping, automatic cruise control

Social and ethical implications

  • Myth
    • Killer robots will enslave us
  • Reality
    • Deep learning (and more generally, artificial intelligence) will have a profound effect on our society
      • Legal, social, philosophical, political, and personal
In [ ]: