Professional Documents
Culture Documents
Machine Learning
Machine Learning
AYEBALE CHARITY
20/U/0412
1
Contents
1) What is Machine Learning?
2
What is Machine Learning?
Machine Learning is the study of methods for
programming computers to learn.
3
What is Machine Learning?
Learning Trained
algorithm machine
TRAINING
DATA Answer
Query
4
Why machine learning?
Automation of complex and repetitive tasks
Efficiency
Insight generation
Personalization
Optimization
Adaptability
Scalability
Innovation
5
Steps in machine learning
1) Data collection.
2) Representation.
3) Modeling.
4) Estimation.
5) Validation.
6
General structure of a learning system
Learning system
Problem Solving
Teacher
Results
Performance
Evaluation
7
Advantages of ML
1) Can capture complex relationships/functions including
non-linear relationships that may model the underlying
process more effectively.
2) Solving vision problems through statistical inference.
3) Can handle very large datasets obtained from different
sources e.g., multi-omics, in-situ spectra.
4) Intelligence from the common sense AI.
5) Reducing the constraints over time achieving complete
autonomy.
8
Disadvantages of ML
1) Large amounts of data are usually required for efficient
model training
2) Often slow to optimize – may need high computational
power
3) Complicated to set up and therefore can often be
incorrectly
4) Application specific algorithms.
9
Types of machine Learning
1) Unsupervised Learning .
2) Semi-Supervised (reinforcement).
3) Supervised Learning.
10
Unsupervised Learning
Studies how input patterns can be represented to
reflect the statistical structure of the overall
collection of input patterns
No outputs are used (unlike supervised learning
and reinforcement learning)
Learner is provided only unlabeled data.
No feedback is provided from the environment
11
Unsupervised Learning
Advantage
Most of the laws of science were developed
through unsupervised learning.
Disadvantage
The identification of the features itself is a
complex problem in many situations.
12
Semi-Supervised (reinforcement)
It is in between Supervised and Unsupervised
learning techniques the amount of labeled and
unlabeled data required for training.
With the goal of reducing the amount of
supervision required compared to supervised
learning.
At the same time improving the results of
unsupervised clustering to the expectations of the
user.
13
Semi-Supervised (reinforcement)
14
Supervised Learning
1) Analogical learning.
15
Analogical Learning
Analogical learning in machine learning refers to the
process of learning from analogies or similarities
between different tasks, domains, or concepts. This
approach is inspired by human cognition, where we
often learn by recognizing similarities between
different situations or concepts and applying
knowledge from one context to another.
16
Learning by Decision Tree
Decision tree learning is a popular machine learning
technique used for both classification and regression tasks.
Decision trees are a type of supervised learning algorithm
that learns a series of hierarchical decision rules based on
the features of the input data.
Decision trees have several advantages, including simplicity,
interpretability, and the ability to handle both numerical
and categorical data.
17
Applications of machine learning
Drug delivery
Medical diagnosis
Iris verification
Hand-written digits
Radar imaging
Speech, face, and target recognition
Finger print
Traffic monitoring
Signature verification
Robotics vision
18
Thank you
19