· What is AI?
· History and Evolution of AI
· Applications of AI in Various Domains
· Ethical and Societal Considerations
· State Space Search
· Uninformed Search Algorithms (e.g., BFS, DFS)
· Informed Search Algorithms (e.g., A*)
· Heuristic Functions
· Local Search (e.g., Hill Climbing, Simulated Annealing)
· Introduction to machine learning and its types
· Supervised, unsupervised, and reinforcement learning
· Data preprocessing and feature engineering
· Linear regression
· Logistic regression
· Decision trees
· Random forests
· Support vector machines (SVM)
· Evaluation metrics for classification and regression
· Clustering algorithms: K-means, hierarchical clustering, DBSCAN
· Dimensionality reduction: PCA, LDA
· Association rule mining
· Introduction to artificial neural networks (ANNs)
· Feedforward neural networks
· Convolutional neural networks (CNNs)
· Recurrent neural networks (RNNs)
· Training techniques: Backpropagation, optimization algorithms
· Deep learning frameworks: TensorFlow, PyTorch
· Text preprocessing and tokenization
· Word embeddings: Word2Vec, GloVe
· NLP tasks: Sentiment analysis, named entity recognition, language translation
· Sequence-to-sequence models
· Attention mechanisms
· Image preprocessing
· Convolutional neural networks for image classification and object detection
· Transfer learning in computer vision
· Applications of computer vision: Face recognition, image generation
· Basics of reinforcement learning
· Markov decision processes (MDPs)
· Q-learning and Deep Q Networks (DQNs)
· Policy-based methods and actor-critic methods
· Generative Adversarial Networks (GANs)
· Transfer learning and domain adaptation
· Explainable AI
· AI in robotics and autonomous systems
· Bias and fairness in AI
· AI and privacy
· AI and jobs: Automation and societal impact
· Responsible AI development and deployment
Course Review