Python and Math for Machine Learning

1. Python programming fundamentals

2. Essentials of Linear Algebra, Probability, Statistics, Differential Calculus

3. Dask, PyTorch, Bokeh for large data handling and large data visualizations

4. Writing clean, modular, and efficient code

Foundations of Machine Learning

1. Supervised, unsupervised and reinforcement Learning

2. Model selection and evaluation

3. Feature engineering & data preprocessing

4. Cost functions and gradient descent

5. Key algorithms: Multiple linear regression, Logistic regression, Decision trees, k-Means, PCA

Data Analysis

1. Exploratory Data Analysis (EDA)

2. Handling missing values, outliers, and noise

3. Data visualization with Bokeh

4. Feature types, distributions, correlation, and trends

5. Working with time-indexed data

6. Trend, seasonality, autocorrelation

7. Forecasting models: ARIMA, Prophet

Deep Learning & Computer Vision

1. Neural networks and backpropagation

2. Convolutional Neural Networks (CNNs)

3. Image classification, object detection, transfer learning

4. Tools: PyTorch

Deep Learning for NLP

1. Text preprocessing and embeddings

2. Very brief history of NLP field

3. Transformers and Attention mechanism

4. Sequence modeling, sentiment analysis, text generation

Local LLM and Prompt Engineering

1. Working in LLMs locally

2. Types of LLMs and their applications

3. Advance prompt engineering

Capstone

1. Project proposals

2. Team formation, work distribution

3. Development and hosting

4. Demo