📚 Data Analytics, ML and AI Using Python Course Curriculum
| Module |
Duration (in Hours) |
Recap of Python
- Quick revision of Python
- Quick recap on OOPS
- Best practices
- Logging
- Exception handling
- Python Debugger (PDB)
- Parallelism (Multi threading and Multi processing)
- Importing libraries (From Vs Import)
- Virtual Environment
- Important Modules
- OS
- Sys
- Time
- Subprocess
- JSON
|
2 |
Fundamentals of Data Analytics
- Overview
- Data Collection and Preprocessing
- Data Cleaning / Data Cleansing
- Data Munging / Data Wrangling
- Data Transformation
- Feature Engineering
- Data Reduction
- Outlier Detection and Handling
- Data Integration
- Data Spitting
- Exploratory Data Analysis(EDA)
- Descriptive Statistics
- Data Visualization
- Outliar Detection
- Missing Value Analysis
- Correlation Analysis
- Dimensionality Reduction
- Hypothesis Generation
- Visualization techniques using libraries Matplotlib,Seaborn, Plotly, Bokeh and Altair
- Univariate Data Visualization
- Bivariate Data Visualization
- Multivariate Data Visualization
- Geospatial Visualization
- Network Visualization
- Advanced and Interactive Visualizations
- Dimensionality Reduction Visualizations
|
8 |
Python Modules for ML/AI
- Pandas
- NumPy
- Matplotlib
- Seaborn
- Scikit Learn
- TensorFlow
- PyTorch
- OpenCV
- Keras
- NLTK
|
4 |
Natural Language Processing (NLP)
- Text Preprocessing
- Tokenization (word and sentence-level)
- Stopword removal
- Stemming and lemmatization
- Text normalization (lowercasing, removing punctuation, etc.)
- Handling missing or noisy text data
- Syntax and Structure
- Part-of-Speech (POS) tagging
- Parsing (syntax and dependency parsing)
- Named Entity Recognition (NER)
- Chunking (phrase recognition)
- Semantic Analysis
- Word embeddings (e.g., Word2Vec, GloVe, FastText)
- Contextual embeddings (e.g., BERT, GPT)
- Sentiment analysis
- Topic modeling (e.g., Latent Dirichlet Allocation - LDA)
- Semantic similarity and word sense disambiguation
- Text Representation
- Bag of Words (BoW)
- Term Frequency-Inverse Document Frequency (TF-IDF)
- Vectorization techniques for numerical representation
- Machine Translation
- Rule-based translation
- Statistical machine translation (SMT)
- Neural machine translation
- Text Generation
- Language modeling
- Text summarization (extractive and abstractive)
- Story or content generation using transformers
- Question Answering and Chatbots
- Reading comprehension tasks
- Conversational agents
- Intent recognition and response generation
- Speech and Text Interface
- Speech-to-Text (STT) and Text-to-Speech (TTS) conversion
- Audio analysis integrated with NLP
- Advanced Techniques
- Transfer learning (e.g., fine-tuning BERT or GPT)
- Attention mechanisms (e.g., Transformers)
- Sequence-to-sequence models
- Reinforcement learning in conversational AI
- Applications
- Document classification
- Spam filtering
- Plagiarism detection
- Social media analysis
|
8 |
Basics: Machine Learning
- Types:
- Supervised learning
- Unsupervised learning
- Reinforcement learning
- Model evaluation and validation
|
2 |
Supervised Learning Algorithms
- Regression Algorithms
- Linear Regression
- Polynomial Regression
- Ridge Regression
- Lasso Regression
- Elastic Net
- Classification Algorithms
- Logistic Regression
- Support Vector Machines (SVM)
- k-Nearest Neighbors (k-NN)
- Decision Trees
- Random Forests
- Gradient Boosted Machines (e.g., XGBoost, LightGBM, CatBoost)
- Naive Bayes (Gaussian, Bernoulli, Multinomial)
- Neural Network-based Algorithms
- Feedforward Neural Networks
- Convolutional Neural Networks (CNNs) (image data)
- Recurrent Neural Networks (RNNs) (time series data)
- Deep Neural Networks (DNNs)
- Ensemble Learning Techniques
- Bagging (e.g., Random Forest)
- Boosting (e.g., AdaBoost, Gradient Boosting, XGBoost, LightGBM)
- Stacking (meta-models)
- Bayesian Algorithms
- Bayesian Networks
- Gaussian Processes
- Dimensionality Reduction
- Principal Component Regression (PCR)
- Partial Least Squares Regression (PLSR)
|
8 |
Un-Supervised learning Algorithms
- Clustering Algorithms
- K-Means Clustering
- Hierarchical Clustering
- DBSCAN (Density-Based Spatial Clustering of Applications with Noise)
- Gaussian Mixture Models (GMM)
- Mean-Shift Clustering
- Dimensionality Reduction Algorithms
- Principal Component Analysis (PCA)
- t-Distributed Stochastic Neighbor Embedding (t-SNE)
- Singular Value Decomposition (SVD)
- Independent Component Analysis (ICA)
- UMAP (Uniform Manifold Approximation and Projection)
- Association Rule Learning Algorithms
- Apriori Algorithm
- Eclat Algorithm
- FP-Growth (Frequent Pattern Growth)
- Anomaly Detection Algorithms
- Isolation Forest
- One-Class SVM
- Autoencoders (for unsupervised anomaly detection)
- Neural Network-based Algorithms
- Self-Organizing Maps (SOM)
- Autoencoders (used for dimensionality reduction and feature learning)
- Restricted Boltzmann Machines (RBM)
- Density Estimation Techniques (Estimate data distribution)
- Kernel Density Estimation (KDE)
- Gaussian Mixtures
|
8 |
Reinforcement Learning Algorithms
- Value-Based Algorithms
- Q-Learning
- SARSA (State-Action-Reward-State-Action)
- Deep Q-Networks (DQN)
- Policy-Based Algorithms
- REINFORCE
- Actor-Critic Algorithms
- Variants include A2C (Advantage Actor-Critic) and A3C (Asynchronous Advantage Actor-Critic).
- Model-Based Algorithms
- Algorithms that involve building a model of the environment and planning based on it, such as Dyna-Q
- On-Policy vs. Off-Policy Algorithms
- Advanced Techniques
- Proximal Policy Optimization (PPO)
- Trust Region Policy Optimization (TRPO)
- Soft Actor-Critic (SAC)
- Deep Deterministic Policy Gradient (DDPG)
- Twin Delayed DDPG (TD3)
- Multi-Agent RL Algorithms
- Cooperative and Competitive Learning
- Hierarchical RL Algorithms
- Algorithms that involve learning hierarchies or sub-policies to solve complex tasks.
|
8 |
Role of ML in AI
- Learning from Data
- Decision-Making
- Adaptability
- Automation of Tasks
- Real-Time Predictions and Insights
- Natural Language Processing (NLP
- Reinforcement Learning for Dynamic Environments
|
4 |
Artificial Intelligence
- Fundamentals of AI
- Introduction to AI: History, applications, and future trends.
- Machine Learning (ML): Supervised, unsupervised, and reinforcement learning.
- Deep Learning: Neural networks, backpropagation, and activation functions.
- Intermediate AI Concepts
- Computer Vision: Image recognition, object detection, and generative models.
- Natural Language Processing (NLP): Text processing, sentiment analysis, and chatbots.
- AI Ethics & Bias: Fairness, transparency, and responsible AI development.
- LLM (Large Language Models)
- Transformer Architecture: The foundation of LLMs like GPT and BERT.
- Natural Language Processing (NLP): How LLMs process and generate human-like text.
- Fine-Tuning & Prompt Engineering: Optimizing LLMs for specific tasks.
- Ethics & Bias in AI: Addressing fairness and responsible AI development.
- Multimodal AI: Combining text, images, and audio in AI models.
- Generative AI Models
- GANs (Generative Adversarial Networks): Used for image generation and deepfake creation.
- Diffusion Models: Used in AI art generation (e.g., DALL·E, Stable Diffusion).
- Variational Autoencoders (VAEs): Used for generating synthetic data
- Specialized AI Models
- Vision-Language Models (VLMs): Combine text and images (e.g., CLIP)
- Speech Recognition Models: Convert speech to text (e.g., Whisper)
- Recommendation Systems: Suggest content based on user behavior (e.g., Netflix’s recommendation engine)
|
8 |
| Total |
60 |