MACHINE AND
DEEP LEARNING:
AN OVERVIEW
BY VARNIKA SOOD
MACHINE LEARNING
AND DEEP LEARNING
1
Machine Learning
Machine learning is the art of science of getting computers to act
as per the algorithms designed and programmed. Many
researchers think machine learning is the best way to make
progress towards human-level AI.
Machine learning includes the following types of patterns:
• Supervised learning pattern
• Unsupervised learning pattern
Uses of ML
Email spam
filtering
Product
recommendations
Online fraud
detection
How does Machine Learning work?
Deep Learning
Deep Learning is the subset of machine learning or can be said as
a special kind of machine learning.
It works technically in the same way as machine learning does, but
with different capabilities and approaches.
It is inspired by the functionality of human brain cells, which are
called neurons, and leads to the concept of artificial neural
networks. It is also called a deep neural network or deep neural
learning.
Uses of DL
Self-driving
cars
Natural language
processing
Language
translation
How does Deep Learning work?
LEARNING MODELS
2
Generative
Learning
Model
Discriminative
Learning
Model
How do they differ ?
Generative Learning Models
• Probabilistic ‘model’ of each class
• Decision boundary:
where one model becomes more likely
• Natural use of unlabelled data
Discriminative Learning Models
• Focus on the decision boundary
• More powerful with lots of examples
• Not designed to use unlabelled data
• Only supervised tasks
Let’s see
an example !
ARTIFICIAL NEURAL NETWORK
(ANN)
3
Artificial Neural Network
• Computational model in view of the structure and elements of
natural neural systems
• Data that moves through the systems influences the structure
of the ANN in light of the fact that a neural system changes
• A manufactured neural system is an interconnected gathering
of nodes same as the immense system of neurons in our brain
DEEP BELIEF NETWORK
(DBN)
4
Deep Belief Network
• Feed forward neural network with a deep architecture or many
hidden layers
• DBNs were invented to overcome the many demerits of the
prior widely used neural network
• Uses layer-by-layer approach of neural networks and consists
of visible units as well as hidden units, one for each class of
layer
IMPLEMENTATION TECHNIQUES
5
Unsupervised
Learning
Machine
Learning
Reinforcement
Learning
Supervised
Learning
Clustering Regression
machine learning and neural technology

machine learning and neural technology