3. What is machine learning?
"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 tasks in T, as measured by P, improves with experience E."
- Tom M. Mitchell (Professor at Carnegie Mellon University)
Machine learning is an application of artificial intelligence (AI) that provides
systems the ability to automatically learn and improve from experience without
being explicitly programmed. Machine learning focuses on the development
of computer programs that can access data and use it learn for themselves.
4. The Evolution -
Experiences Data Problem/Task
Bias Performance
The term “Machine Learning” was
first coined by Arthur Samuels.
•1950s:–Samuel's checker-playing
program
•1960s:–Neural network:
Rosenblatt's perceptron
•1970s:–Natural language
processing.
•1980s:–Advanced decision tree
and rule learning , Resurgence of
neural network
1994 - Google’s Self Driving car
1997 - Deep Blue beats Gary
Kasparov LEARNER MODEL
5. Why a sudden boom in
AI and Machine
Learning?
● High performance
machine
● Lots and lots of
data
7. Google's deep learning AI system can detect cancer faster, and with higher
accuracy than human professionals.
8. TEXT MINING BUSINESS INTELLIGENCE/RISK
MANAGEMENT
ORACLE , MICROSOFT AND SAP HAVE 98% ACCURATE
INTEGRATED BUSINESS AI ALGORITHMS WHICH AWARES
THEM FROM HIGH RISKS AND PROVIDES STATISTICAL MODELS.
15. This Black box
contains Millions of
Random Images with
ground truths.
Classifier 1
Classifier 2
Classifier 3
Step 1 :
Clustering -
Unsupervised
Learning
Step 2 :
Supervised
Learning
17. Deep Learning
Deep Learning is primarily
about neural networks, where
a network is an interconnected
web of nodes and edges.
Neural nets were designed to
perform complex tasks, such
as the task of placing objects
into categories based on a few
attributes. This process,
known as classification.
18. ● Each node in the hidden
and output layers has a
classifier.
● The input neurons
receive the data
features. After
processing the data,
they send output to the
first hidden layer.
● The hidden layer
processes this output
and sends results to the
next hidden layer.
● The data reaches the
final output layer, where
the output value
determines the object's
classification.
● Process is known as
Forward Propagation, or
Forward prop.
19. Weights and Biases
Before a neuron fires its output to the
next neuron in the network, it must first
process the input. To do so, it performs
a basic calculation with the input and
two other numbers, referred to as the
weight and the bias.
0.1
0.2
0.3
0.4
0.5
Value is processed
using some
mathematical
operations
21. 784 16 16
10
Value of neuron in next layer
X = sigmoid(w(0,0)*v(0,0)+w(0,1)*v(0,1)+
…...w(0,784)*v(0,784) + b(0))
Sigmoid function
w = weight
b = bias
784x16 + 16x16 + 16x10 weights
16 + 16 + 10 Biases
13,002
22. SAURAV PRASAD SAIF ARSALAN
sauravprasad.1996@gmail.com saifsocial2711@gmail.com
THANK YOU !