1. Introduction to Deep Learning
Jitender Chauhan
Senior Engineer
jsinghchauhan@salesforce.com
2. Introduction to Learning
What is Machine learning ?
Field of study that gives computers the ability to learn
without being programmed explicitly
By: Arthur Samuel
A computer program is said to learn from experience E
with respect to some task T and some performance
measure P , if its performance on T , as measured by P,
improves with experience E
By: Tom Mitchell
3. How Machine learning is different from
Artificial Intelligence ?
● Artificial Intelligence is the study of how to create intelligent agents.
● It is how to program a computer to behave as an intelligent agent (say, a person).
● This does not have to involve learning or induction at all.
● Artificial Intelligence uses models built by Machine Learning
6. Supervised Learning
● Learning from Labelled Data
Ex:
● Predicting price of a house using available
data set containing house area and house
price.
● Deciding whether to approve/reject credit
card application using existing customer
records.
● Predicting whether a message is spam or
non spam using existing labelled data set
7. Unsupervised Learning
● Learning from unlabelled data
● Grouping data in categories based on similarities between
them
Ex:
● Summarize the news for the past month ànd cluster them
● Fraud Detection
● Anomaly Detection
8. ● Learning with labelled and unlabelled Data
● 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
Semi supervised Learning
Reinforcement Learning
● Reinforcement learning is the problem of getting an agent to act in the world so as to
maximize its rewards.
Ex
● Consider teaching a dog a new trick: you cannot tell it what to do, but you can reward/punish
it if it does the right/wrong thing. It has to figure out what it did that made it get the
reward/punishment, which is known as the credit assignment problem.
9. ● filters information by using the recommendations of other
people.
Ex:
● A person who wants to see a movie, might ask for
recommendations from friends. The recommendations of
some friends who have similar interests are trusted more
than recommendations from others. This information is
used in the decision on which movie to see.
Apps:
● Recommendation System
Collaborative Learning (Filtering)
10. ● On-line learning algorithms take an initial guess model
and then picks up one-one observation from the training
population and recalibrates the weights on each input
parameter.
Ex:
● Learning User’s interest and behave accordingly
Online Learning
16. ● The Branch of study that tries to mimic Human Brain
● The main concept in deep learning algorithms is
automating the extraction of representations from the data
● Deep learning algorithms use a huge amount of
unsupervised data to automatically extract complex
representation.
Deep Learning
17. ● Image Classification
● Speech Recognition
● Natural Language Processing
● Optical Character Recognition
Deep Learning Applications