Week 1: Introduction to Deep Learning

Overview of Artificial Intelligence and Machine Learning

Definitions and scope

Real-world applications

Introduction to Deep Learning

Differences between Machine Learning and Deep Learning

Key components of Deep Learning

Popular Deep Learning frameworks (TensorFlow, PyTorch)

Mathematical Foundations

Linear algebra basics

Probability and statistics review

Introduction to calculus for optimization

Week 2: Neural Networks Fundamentals

Structure of a Neural Network

Neurons, layers, and activation functions

Forward and backward propagation

Loss functions

Types of Neural Networks

Artificial Neural Networks (ANNs)

Recurrent Neural Networks (RNNs)

Convolutional Neural Networks (CNNs)

Training Neural Networks

Gradient descent and optimization algorithms

Hyperparameter tuning

Week 3: Deep Learning with TensorFlow and PyTorch

Introduction to TensorFlow

Basic operations and tensors

Building and training a simple neural network

Introduction to PyTorch

PyTorch tensors and operations

Training neural networks using PyTorch

Week 4: Convolutional Neural Networks (CNNs)

Understanding CNNs

Convolutions and pooling layers

Applications of CNNs in Image Processing

Building CNN Models

Implementing CNNs using TensorFlow and PyTorch

Transfer learning with pre-trained models

Week 5: Recurrent Neural Networks (RNNs) and NLP

 Understanding RNNs

Sequential data and RNN architecture

Long Short-Term Memory (LSTM) networks

Gated Recurrent Units (GRUs)

1.  Foundations of NLP

Introduction to NLP

Introduction to Natural Language Processing

What is NLP?

Applications of NLP (chatbots, sentiment analysis, etc.)

Basic concepts: tokens, stemming, lemmatization, stop words, etc.

Text Preprocessing

Tokenization (word and sentence tokenization)

Removing stop words

Stemming and Lemmatization

Part-of-speech tagging

Named Entity Recognition (NER)

 Linguistic Foundations

 Syntax and Parsing

Constituency Parsing

Dependency Parsing

Morphology

Word formation

Affixes and roots

Semantics

Word sense disambiguation

Semantic roles and relations

  Latent Dirichlet Allocation (LDA)

Text Representation Techniques

Bag of Words (BoW)

TF-IDF (Term Frequency-Inverse Document Frequency)

Word Embeddings

• Word2Vec
• GloVe
• FastText 

Week 9-10: Language Models

1.  Foundations of Time Series

Introduction to Time Series

What is Time Series?

Definition, components: trend, seasonality, noise, and cyclicity

Examples of time series in real-world applications (stock prices, weather data, etc.)

Time Series Data

Types of time series (univariate vs. multivariate)

Time series as ordered data

Time series and autocorrelation. 

Basic Time Series Concepts

 Time Series Decomposition

Additive vs. multiplicative models

Trend, seasonality, and residual components

Moving averages (simple, weighted)

Stationarity in Time Series

Stationary vs. non-stationary series

Unit root test (Dickey-Fuller test)

Differencing to achieve stationarity

Autocorrelation and Partial Autocorrelation

Understanding autocorrelation functions (ACF)

Partial Autocorrelation Function (PACF)

Autocorrelation plots

2.  Time Series Analysis Techniques Forecasting Methods      

Naive Forecasting Methods

Simple average

Naive and seasonal naive methods

Exponential Smoothing

Simple Exponential Smoothing

Holt’s Linear Trend Model

Holt-Winters Seasonal Model

Autoregressive Integrated Moving Average (ARIMA)

 AR, MA, ARMA models

Differencing and the ARIMA model (p, d, q)

Model selection using AIC, BIC, and grid search

Advanced Time Series Models

Seasonal ARIMA (SARIMA)

Seasonal differencing

SARIMA model structure (P, D, Q) 

Autoregressive Conditional Heteroskedasticity (ARCH) and GARCH Models

Understanding volatility modeling

GARCH(1,1) model for financial time series