Artifical Intelligence
AI 3 MONTHS COURSE CONTENT
Weeks 1 - 2: Introduction and Foundations
Day 1-2: Introduction to AI
- History, types (narrow, general, super AI).
- Applications of AI in different industries.
Day 3-5: Python for AI
- Basic Python concepts, libraries (NumPy, Pandas, Matplotlib).
- Understanding AI development tools (Jupyter Notebook, Google Colab).
Day 6-7: Math for AI
- Linear algebra (vectors, matrices, eigenvalues).
- Probability and statistics basics.
Day 8-10: Logic and Search Algorithms
- State-space representation, BFS, DFS, A*.
- Optimization concepts: Hill climbing, Simulated Annealing.
Day 11-12: Data Preprocessing
- Data cleaning, scaling, normalization.
- Encoding categorical data, feature selection.
Day 13-14: Introduction to Machine Learning
- Supervised, unsupervised, and reinforcement learning.
- Algorithms overview: Regression, classification, clustering.
Weeks 3-4: Machine Learning
Day 15-17: Regression Models
- Linear Regression, Polynomial Regression.
- Evaluation metrics (R², RMSE).
Day 18-20: Classification Models
- Logistic Regression, Naive Bayes, Decision Trees.
- Model evaluation (confusion matrix, ROC-AUC).
Day 21-23: Clustering
- K-Means, Hierarchical clustering.
- Evaluation metrics (silhouette score, Davies-Bouldin index).
Day 24-25: Feature Engineering and Feature Scaling
- PCA, dimensionality reduction.
- Techniques for improving model performance.
Day 26-28: Ensemble Methods
- Random Forest, Gradient Boosting (XGBoost, CatBoost, LightGBM).
- Stacking and voting classifiers.
Weeks 5-6: Neural Networks and Deep Learning Basics
Day 29-31: Introduction to Neural Networks
- Perceptrons, activation functions (ReLU, Sigmoid, Tanh).
- Feedforward networks and backpropagation.
Day 32-34: Deep Learning Basics
- Introduction to TensorFlow and PyTorch.
- Building simple neural networks.
Day 35-37: Convolutional Neural Networks (CNNs)
- CNN architecture, convolution layers, pooling layers.
- Applications in image recognition.
Day 38-39: Recurrent Neural Networks (RNNs)
- Sequence modeling, LSTMs, GRUs.
- Use cases in time series and text.
Day 40-42: Optimization in Deep Learning
- Gradient descent, learning rate scheduling.
- Regularization techniques (dropout, weight decay).
Weeks 7-8: Advanced AI Topics
Day 43-45: Natural Language Processing (NLP) Basics
- Tokenization, stemming, lemmatization.
- Word embeddings (Word2Vec, GloVe).
Day 46-48: Advanced NLP
- Transformers and BERT architecture.
- Applications in sentiment analysis and chatbots.
Day 49-50: Generative AI Basics
- GANs (Generative Adversarial Networks).
- Applications in image and video generation.
Day 51-53: Reinforcement Learning
- Markov Decision Processes (MDPs), Q-Learning.
- Deep Q-Networks (DQN).
Day 54-56: AI Ethics and Fairness
- Bias in AI models.
- Explainability and interpretability.
Weeks 9-10: Real-World Applications and Projects
Day 57-60: AI in Computer Vision
- Object detection (YOLO, Faster R-CNN).
- Image segmentation (U-Net).
Day 61-63: Advanced Generative Models
- Diffusion models, Stable Diffusion.
- Applications in art and text-to-image generation.
Day 64-66: AI in Healthcare and Business
- Use cases in diagnostics, predictive analytics, and marketing.
Day 67-70: End-to-End AI Project (1)
- Dataset selection, preprocessing, model building, deployment.
Weeks 11-12: Advanced Research and Portfolio
Day 71-74: Large Language Models (LLMs)
- Understanding GPT architecture.
- Fine-tuning and prompt engineering.
Day 75-77: AI Deployment
- Deploying models using Flask/Django.
- MLOps pipelines and scaling solutions.
Day 78-81: Real-World AI Challenges
- Kaggle competitions, AI ethics debates.
- Exploring edge AI and IoT integration.
Day 82-86: Capstone Project (2)
- Focus on generative AI, reinforcement learning, or computer vision.
Day 87-90: Portfolio Building and Final Review
- Documenting projects, creating a GitHub portfolio.
- Resume and LinkedIn optimization for AI roles.
Note: AI Interview Q & A’s will be provided.
5 Data Science Projects which are resumed based will be provided as Bonus for this Course.