2. WHAT IS LEARNING?
• Process of learning begins with observation of data such as, examples,
direct experience or instructions.
• Its aim is to allow the computers learn automatically without human
intervention or assistance and adjust actions accordingly.
4. SUPERVISED MACHINE LEARNING
• Can apply what has been learned in the past to new data using labeled
examples to predict future events.
• Starting from the analysis of a known training dataset, the learning
algorithm produces an inferred function to make predictions about the
output values.
• Algorithm analyzes the training data set and produces an inferred
function.
• If the output of the function is discrete than it is called classifier and if
the output is continuous than it is called a regression function.
5. EXAMPLE
• If the inputs are 1,2,3,4,5,6 and the outputs according to the inputs are
1,4,9,16,25,36
• Then we can predict the next output by the help of function which we
get from above which is output=input^2
• So if the next input is 7 than by putting in function the output will be 49
7. UNSUPERVISED MACHINE LEARNING
• No labels are given to the learning algorithm, leaving it on its own to
find structure in its inputs
• Unsupervised learning can be a goal in itself (discovering hidden
patterns in data).
• The data have no target attribute.
8. EXAMPLE
• You have bunch of photos of 6 people but without information who is
on which one and want to divide this dataset into 6 piles, each with
photos of one individual.
10. SEMI-SUPERVISED LEARNING
• Semi-supervised learning falls in between Supervised and Unsupervised.
• Semi-supervised learning use small amount of labeled data and large
amount of unlabeled data.
• The goal is to learn a predictor that predicts future test data better than
the predictor learned from the labeled training data alone.
• This for example can be used in Deep belief networks, where some
layers are learning the structure of the data (unsupervised) and one
layer is used to make the classification (trained with supervised data)
11. REINFORCEMENT MACHINE LEARNING
ALGORITHMS
• Is a learning method that interacts with its environment by producing actions and
discovers errors or rewards.
• Reinforcement learning algorithm (called the agent) continuously learns from the
environment in an iterative fashion. In the process, the agent learns from its
experiences of the environment until it explores the full range of possible states.
• This method allows machines and software agents to automatically determine the
behavior within a specific context in order to maximize its performance
12. STEPS REINFORCEMENT ALGO WORK..
• In order to produce intelligent programs (also called agents), reinforcement learning
goes through the following steps:
• Input state is observed by the agent.
• Decision making function is used to make the agent perform an action.
• After the action is performed, the agent receives reward or reinforcement from the
environment.
• The state-action pair information about the reward is stored.