Here in this presentation you will get definitions of ML as well as its types with examples and some of well known applications.you may find a bit difficulty in slide 6 but please download the ppt and run on your PC.I am sure you will not disappoint
2. 1.What is Machine Learning?
2.Examples of Machine Learning
1.Supervised Learning
2.Unsupervised Learning
3.Reinforcement Learning
Introduction
Types Of Machine Learning
Importance of Maths in Machine Learning
Applications of Machine
Learning
1.Facial Recognition
2.Self-customizing Programs (Netflix,
3.Amazon, etc.
4.Speech Recognition
5.Other Applications
3. What is Machine Learning?
Arthur Samuel (1959) Machine Learning:
Field of study that gives computers the ability
to learn without being explicitly programmed.
Tom Mitchell (1998) :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.
5. Supervised
Learning During supervised learning, a machine is given data, known
as training data in data mining parlance, based on which the
machine does classification.
Types:
Classification: Machine is trained to classify something into
some class.
classifying whether a patient has disease or not
Regression: Machine is trained to predict some value like price,
weight or height.
Algorithm
5,6
11
Logic
Predicting with new data
62,4
Training with Training data
Logic
6. Supervised
LearningCheck weather Breast Cancer is Malignant or Benign
malignant
Tumor size
1(YES)
0(NO)
This is an example of
classification
problem
Age
Tumor
Benign
Malignant
7. The training data does not include targets here so we don’t
tell the system where to go , the system has to understand
itself from the data we give.
Types:
Clustering: This is a type of problem where we group similar
things together.
given a set of tweets ,cluster based on content of tweet
Anomaly detection
AlgorithmUnstructured Data Results/Conclusion
Understand
patterns in
data itself
9. Reinforcement Learning
Reinforcement learning (RL) is an area of machine
learning concerned with how software agents ought to
take actions in an environment so as to maximize some
notion of cumulative reward.
Video games are a common test environment for this kind
of research.
+1
-1
E
X
A
M
P
L
E
10. Linear Algebra
Topics such as QR Decomposition/Factorization, Symmetric Matrices, Matrix Operations,
Projections, Vector Spaces and Norms are needed for understanding the optimization
methods used for machine learning.
Probability Theory and Statistics
Some of the fundamental Statistical and Probability Theory needed for ML are Combinatorics,
Probability Rules & Axioms, Bayes Theorem, Random Variables, Variance and Expectation,
Standard Distributions (Bernoulli, Binomial, Multinomial, Uniform and Gaussian), and Sampling
Methods.
Multivariate Calculus: Some of the necessary topics include Differential and Integral
Calculus, Partial Derivatives, Vector-Values Functions, Directional Gradient, Hessian,
Jacobian, Laplacian and Lagragian Distribution.
Algorithms and Complex Optimizations: This is important for understanding the
computational efficiency and scalability of our Machine Learning Algorithm and for
exploiting sparsity in our datasets. Knowledge of data structures (Binary Trees, Hashing,
Heap, Stack etc), Dynamic Programming, Randomized & Sublinear Algorithm, Graphs,
Gradient/Stochastic Descents and Primal-Dual methods are needed.
11. 35%
25%
15%
15%
10%
Importance of Maths Topics Needed For
Machine Learning
Linear Algebra
Probability &
Statistics
Multivariate
Calculus
Algorithm &
Complexity
Others
Others: This comprises of other
Math topics not covered in the
four major areas described
above. They include Real and
Complex Analysis (Sets and
Sequences, Topology, Metric
Spaces, Single-Valued and
Continuous Functions, Limits,
Cauchy Kernel, Fourier
Transforms), Information Theory
(Entropy, Information Gain),
Function Spaces and Manifolds.
13. Face Recognition
In face recognition, the image first prepared for
preprocessing and then trained the face recogniser to
recognise the faces. After teaching the recogniser, we
test the recogniser to see the results.
Speech recognition is the inter-disciplinary sub-field
of computational linguistics that develops methodologies and
technologies that enables the recognition and translation of spoken
language into text by computers. It is also known as automatic
speech recognition (ASR), computer speech
recognition or speech to text (STT).