Introduction of Machine learning and Deep Learning

About Me
Madhu Babu Sanjeevi,
Software Engineer,
Languages C, Java, Python
Technologies Machine Learning, Deep Learning,
NLP, Big data, Mobile dev.
Developments Android, Web, Rest API
Databases SQL, Mongo DB
Madhu Sanjeevi Madhu009 Madhu.ai

Agenda
•1.Introduction of Machine learning & Deep
learning
•2.Various learning algorithms of ML & DL
•3.Applications of ML & DL
•4.Open Source tools and help
•5.Deep Learning Demo

Why Machine Learning????
1 + 1 =11
2 + 2 =22
3 + 3 =?
If 1 + 2 = 10
2 + 3 = 21
7 + 8 = ?
• No hard coded rules
• No Code change

How does it work??
Computer
Data
Program
Output
Computer
Data
Output
Program
Traditional Programming
Machine Learning

What is Machine Learning???
1.Learn from past experiences
2.Improve the performances of intelligent programs
Definitions (Mitchell 1997)
“A computer program is said to learn from experience E with
respect to some class of tasks T and performance measure P,
if its performance at the tasks improves with the experiences”

Supervised Learning
• 1. Training data includes both the input and the desired
results.
• 2. For some examples the correct results (targets) are
known and are given in input to the model during the
learning process.
• 3. These methods are usually fast and accurate.

Classification: for categorical response values, where the data can be
separated into specific “classes”.
Regression: for continuous-response values

Unsupervised Learning
• 1. The model is not provided with the correct results during
the training.
• 2. The model has to understand it by itself by extracting
patterns.
• 3. These methods are difficult to implement.

Clustering: grouping similar things together

Introduction of Neural Networks?
• What are Neural Networks?
• Neural networks are a new method of programming computers.
• In the human brain, a typical neuron collects signals from others through a
host of fine structures called dendrites.
• The neuron sends out spikes of electrical activity through a long, thin stand
known as an axon, which splits into thousands of branches.

Diagram of an NN
Fig: A simple Neural Network

Network Layers
• Input Layer - The activity of the input units represents the
raw information that is fed into the network.
• Hidden Layer - The activity of each hidden unit is
determined by the activities of the input units and the
weights on the connections between the input and the
hidden units.
• Output Layer - The behavior of the output units depends
on the activity of the hidden units and the weights
between the hidden and output units.

Neural Networks-Types
1. Feed forward network:
SLP (Single Layer perceptron):
MLP (Multi Layer Perceptron):
2. RNN (Recurrent Neural Network):
3. CNN (Convolution neural Network):
4.TDNN (Time Delay Neural Network) or Shared Weights Neural
Networks:
5. Hopfield Networks

Applications of ML & DL
• Spam Filtering
• Recommendation Engines
• Advancement in Speech Recognition in the last 3 years
• Advancement in Computer Vision
• Advancement in Natural Language Processing
• Used in all Domains
(Banking, Insurance, Healthcare, etc…)
18

Open Source Tools for DL
DL4J: Torch:
JVM-based Lua based
Distrubted Contains pretrained model
Integrates with Hadoop and Spark
TensorFlow: Theano:
Google written successor to Theano Very popular in Academia
Interfaced with via Python and Numpy Fairly low level
Highly parallel Interfaced with via Python and
Numpy
Caffe:
Not general purpose. Focuses on machine-vision problems
Implemented in C++ and is very fast
Not easily extensible
Has a Python interface

Deep
Learning
Resources
Name Language Link Note
Pylearn2 Python
http://deeplearning.net/softwar
e/pylearn2/
A machine learning library built
on Theano
Theano Python
http://deeplearning.net/softwar
e/theano/
A python deep learning library
Caffe C++ http://caffe.berkeleyvision.org/
A deep learning framework by
Berkeley
Torch Lua http://torch.ch/
An open source machine learning
framework
Overfeat Lua
http://cilvr.nyu.edu/doku.php?i
d=code:start
A convolutional network image
processor
Deeplearning
4j
Java http://deeplearning4j.org/
A commercial grade deep
learning library
Word2vec C
https://code.google.com/p/w
ord2vec/
Word embedding framework
GloVe C
http://nlp.stanford.edu/projects
/glove/
Word embedding framework
Doc2vec C
https://radimrehurek.com/gens
im/models/doc2vec.html
Language model for paragraphs
and documents
StanfordNLP Java http://nlp.stanford.edu/
A deep learning-based NLP
package
TensorFlow Python http://www.tensorflow.org
A deep learning based python
library
20

Introduction of Machine learning and Deep Learning

Introduction of Machine learning and Deep Learning

More Related Content

What's hot

Similar to Introduction of Machine learning and Deep Learning

Recently uploaded

Introduction of Machine learning and Deep Learning