2. Contents
Introduction to ML
Classification of ML
Supervised and semi supervised ML
Touchdown on DL & NN
Implementation of ML in WSN
Real world implementation scenarios of ML
Tools for ML (focus more on TensorFlow rather than
PyTorch or WEKA, as it is a Google open source software)
Resources
3. Introduction to
Machine Learning
Machine learning is a subset of artificial intelligence
(AI) that focuses on enabling computers to learn
from data and improve their performance over
time without being explicitly programmed. In other
words, it's about creating algorithms that can
automatically learn patterns and make predictions
or decisions based on data.
4. Classification of ML
Supervised Learning:
1.
Learn from labeled data.
Examples: Classification, Regression.
Unsupervised Learning:
2.
Learn from unlabeled data.
Examples: Clustering, Dimensionality Reduction.
Semi-Supervised Learning:
3.
Combines labeled and unlabeled data.
Useful when labeled data is scarce/expensive.
Reinforcement Learning:
4.
Learn from interaction with an environment.
Agent learns by receiving rewards or penalties.
Self-supervised Learning:
5.
Uses the structure of the input to generate supervisory signals from
the data itself.
5. Supervised and
Semi-Supervised ML
Supervised Learning:
Learns from labeled data.
Examples include classification (predicting categories) and regression (predicting
continuous values).
Requires a large amount of labeled data for training.
The model learns to map input data to corresponding output labels.
Semi-Supervised Learning:
Utilizes a combination of labeled and unlabeled data.
Labeled data is scarce or expensive to obtain.
The model learns from both labeled and unlabeled data to improve performance.
Often achieves better performance than purely supervised learning when labeled data
is limited.
6. Touchdown on
DL and NN
Neural Networks (NN) are computational models inspired
by the human brain, consisting of interconnected nodes
(neurons) organized into layers. Deep Learning (DL) is a
subset of machine learning that employs neural networks
with many layers to automatically learn representations of
data through multiple layers of abstraction, excelling at
tasks like image recognition and natural language
processing.
7. Implementation of
ML in WSN
Implementation of Machine Learning (ML) in Wireless Sensor
Networks (WSNs) involves deploying ML algorithms directly on the
sensor nodes to enable intelligent decision-making and data
processing at the edge of the network. This allows for real-time
analysis of sensor data, reducing the need for transmitting raw data
to a central location, thus conserving energy and bandwidth. ML
techniques such as anomaly detection, classification, and predictive
modeling can be applied to various WSN applications including
environmental monitoring, surveillance, healthcare, and smart
infrastructure management.
8. Real World implementation
scenarios of ML
Recommendation Systems: Used by platforms like Netflix and
Amazon to suggest products or content based on user
preferences.
Fraud Detection: Financial institutions utilize ML algorithms to
detect fraudulent activities in transactions.
Healthcare Diagnostics: ML helps in medical image analysis,
disease diagnosis, and personalized treatment recommendations.
Autonomous Vehicles: ML algorithms enable self-driving cars to
perceive their surroundings, make decisions, and navigate safely.
Natural Language Processing (NLP): Powers virtual assistants
like Siri and chatbots, enabling human-like interactions with
computers.
9. Tools of ML
TensorFlow is a popular open-source machine learning
framework developed by Google. It offers a range of tools
and libraries for building, training, and deploying machine
learning models efficiently. Some key components include
TensorFlow Core for model development, TensorFlow
Extended (TFX) for production pipelines, TensorFlow Lite
for mobile and embedded devices, and TensorFlow.js for
web-based applications
10. Resources:
DAIR.AI ML Youtube Course (https://github.com/dair-
ai/ML-YouTube-Courses)
Stanford ML Course
(https://github.com/afshinea/stanford-cs-229-
machine-learning)
Nyandwi ML Course
(https://github.com/afshinea/stanford-cs-229-
machine-learning)
Roadmap to ML: https://youtu.be/1vsmaEfbnoE?
si=NgnboBSvr4h-Ca6_