Deep Neural Networks - Notes for lecture 1e

{{< pdf lec1.pdf width="100%" class="ppSlide" >}}

Lecture 1e: Three types of learning

The three main types of learning machine learning:

Supervised learning

Learn to predict an output given an input vector

Reinforcement learning

Learn to select an action to maximize payoff.

Unsupervised learning

Discover a good internal representation of the input.

Semi supervised learning

Semi-supervised uses a small amount of supervised data and large amount of unsupervised elarning

Few/one shot learning

Supervised learning with inference from one or a few examples

Zero shot learning

Supervised learning with inference for inputs not seen in training - usually based on learned structrure

Transfer learning

Learning something from one data set and use it on another

Two types of supervised learning

• Each training case consists of an input vector x and a target output t.
• Regression: The target output is a real number or a whole vector of real numbers.
  • The price of a stock in 6 months time.
  • The temperature at noon tomorrow.
• Classification: The target output is a class label.
  • The simplest case is a choice between 1 and 0.
  • We can also have multiple alternative labels.

How supervised learning typically works

• We start by choosing a model-class:
  • A model-class, f, is a way of using some numerical y=f(x;W) parameters, W, to map each input vector, x, into a predicted output y.
• Learning usually means adjusting the parameters to reduce the discrepancy between the target output, t, on each training case and the actual output, y, produced by the model.
  • For regression, \frac{1}{2}(y-t)^2is often a sensible measure of the discrepancy.
  • For classification there are other measures that are generally more sensible (they also work better).

Reinforcement learning

• In reinforcement learning, the output is an action or sequence of actions and the only supervisory signal is an occasional scalar reward.
  • The goal in selecting each action is to maximize the expected sum of the future rewards.
  • We usually use a discount factor for delayed rewards so that we don’t have to look too far into the future.
• Reinforcement learning is difficult:
  • The rewards are typically delayed so its hard to know where we went wrong (or right).
  • A scalar reward does not supply much information.
• This course cannot cover everything and reinforcement learning is one of the important topics we will not cover.

Unsupervised learning

• For about 40 years, unsupervised learning was largely ignored by the machine learning community
  • Some widely used definitions of machine learning actually excluded it.
  • Many researchers thought that clustering was the only form of unsupervised learning.
• It is hard to say what the aim of unsupervised learning is.
  • One major aim is to create an internal representation of the input that is useful for subsequent supervised or reinforcement learning.
  • You can compute the distance to a surface by using the disparity between two images. But you don’t want to learn to compute disparities by stubbing your toe thousands of times.

Other goals for unsupervised learning

• It provides a compact, low-dimensional representation of the input.
  • High-dimensional inputs typically live on or near a lowdimensional manifold (or several such manifolds).
  • Principal Component Analysis is a widely used linear method for finding a low-dimensional representation.
• It provides an economical high-dimensional representation of the input in terms of learned features.
  • Binary features are economical. – So are real-valued features that are nearly all zero.
• It finds sensible clusters in the input.
  • This is an example of a very sparse code in which only one of the features is non-zero.