Scribd
Upload
2 views2 pages

ML Full Notes

The document provides concise explanations of key concepts in Machine Learning, including its significance, types, and specific methods like Regression and Q-Learning. It also covers various neural network architectures, such as Convolutional Neural Networks and Long Short-Term Memory networks, highlighting their functionalities and applications. Additionally, it discusses the Attention Mechanism in Natural Language Processing.

Uploaded by

santoshkumarsabut
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views2 pages

ML Full Notes

The document provides concise explanations of key concepts in Machine Learning, including its significance, types, and specific methods like Regression and Q-Learning. It also covers various neural network architectures, such as Convolutional Neural Networks and Long Short-Term Memory networks, highlighting their functionalities and applications. Additionally, it discusses the Attention Mechanism in Natural Language Processing.

Uploaded by

santoshkumarsabut
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

SHORT ANSWERS

This section contains clear and exam-ready explanations of all short questions.

Machine Learning

Machine Learning is a subset of Artificial Intelligence where systems learn from data instead of
explicit programming. It is significant because it enables automation, improves accuracy over time,
and is widely used in industries like healthcare, finance, and e-commerce.

Regression

Regression is a supervised learning method used to predict continuous values. It helps in


forecasting and understanding relationships between variables.

Types of Machine Learning

1. Supervised Learning: Uses labeled data. 2. Unsupervised Learning: Finds patterns in unlabeled
data. 3. Reinforcement Learning: Learns through rewards and penalties. Each type has different
use cases such as classification, clustering, and decision making.

Convolutional Neural Network Layers

CNNs consist of convolutional layers, pooling layers, and fully connected layers. Convolution
extracts features, pooling reduces dimensionality, and fully connected layers perform classification.

Q-Learning

Q-Learning is a reinforcement learning algorithm that learns the value of actions in a state. Key
terms include state, action, reward, and Q-value. It is used in robotics and game AI.

Logistic Regression

Logistic Regression is used for classification problems. Types include binary, multinomial, and
ordinal logistic regression.

Multilayer Perceptron

An MLP is a feedforward neural network with multiple layers. It uses activation functions and
backpropagation for learning.
Neural Network Types

Feedforward NN: Data flows one direction. Recurrent NN: Handles sequence data. CNN: Used for
image processing.

LSTM

LSTM is a type of RNN designed to remember long-term dependencies using gates like input,
forget, and output gates.

Attention Mechanism

Attention allows models to focus on important parts of input sequences, improving performance in
NLP tasks like translation.

You might also like