Neural networks used in machine learning (v)

Three types of machine learning

Supervise learning, strengthen learning and unsupervised learning

Types of learning Task
Supervised learning
–learn to predict a output when given an input vector.
Reinforcement Learning
–learn to select a action to maximize payoff.
Unsupervised Learning
–discover a good internal representation of the input

Types of supervised learning
Each training case consists of a input vector x and a target output T.
regression:the target output is a real number or a whole vector of real numbers.
, Haven price of a stock in 6 months time.
, Haven temperature at noon tomorrow.
classification:the target output is a class label.
, Haven simplest case is a choice between 1 and 0.
–we can also has multiple alternative labels.

How supervised learning typically works
We start by choosing a model-class:
–a Model-class, F, is A-on-the-same-a-type using some numerical 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, in each training Case and the actual output, Y, produced by the model.
–for regression, is often a sensible measure of the discrepancy.
–for classification There is other measures that is generally more sensible (they also work better).

Reinforcement learning
Combinatorial reinforcement learning, the output is a action or sequence of actions and the only supervisory signal are an Occasiona L scalar reward.
, haven goal in selecting each action was to maximize the expected sum of the future rewards.
–we usually use a discount factor for delayed rewards so that We don't have the to look too far into the future.
Reinforcement learning is difficult:
, haven rewards is typically delayed so it hard-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'll not cover.

Unsupervised learning
for about years, unsupervised learning were largely ignored by the machine learning Community
–some widely used definitions of machine learning actually excluded it.
–many researchers thought that clustering is the only form of unsupervised learning.
• It is hard-to-say what's the aim of unsupervised learning is.
–one Major aim is to create a internal representation of the input that's useful for subsequent supervised or reinforce ment Learning.
–you can compute the distance to a surface by using the disparity between the images. But your 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 low dimensional manifold (or several such manifolds).
–principal Component analysis was 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 is economical.
–so is real-valued features that is 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.

Neural networks used in machine learning (v)