Artificial Intelligence and Machine Learning

[Buela_Vigneswaran]

Artificial Intelligence and Machine Learning

1. Artificial Intelligence (AI)

 

• Definition:
  • AI involves building systems that can mimic human cognition, such as reasoning, problem-solving, and decision-making.
• Subfields of AI:
  • Expert Systems: AI systems that emulate decision-making by using knowledge bases (e.g., medical diagnosis systems).
  • Search Algorithms:
    • Uninformed Search: Breadth-First Search (BFS), Depth-First Search (DFS).
    • Informed Search: A* Algorithm, Heuristic Search.
  • Game Playing: AI algorithms for chess, Go, and other strategy games.

2. Machine Learning (ML)

 

• Definition:
  • A subset of AI where machines learn from data without being explicitly programmed.
• Types of Machine Learning:
  1. Supervised Learning:
     • Models learn from labeled data (e.g., classification, regression).
     • Algorithms: Linear Regression, Logistic Regression, Support Vector Machines, Decision Trees.
  2. Unsupervised Learning:
     • Models identify patterns in unlabeled data (e.g., clustering, dimensionality reduction).
     • Algorithms: K-Means, DBSCAN, PCA (Principal Component Analysis).
  3. Reinforcement Learning:
     • Agents learn by interacting with an environment and receiving feedback (rewards).
     • Examples: Q-Learning, Deep Q-Networks (DQN).

3. Deep Learning

​​​​​​​

• Overview:
  • A subset of ML focusing on neural networks with many layers.
• Key Concepts:
  • Neural Networks: Input, hidden, and output layers.
  • Activation Functions: ReLU, Sigmoid, Softmax.
  • Backpropagation: Training neural networks by minimizing error.
• Applications:
  • Image Recognition, Natural Language Processing (NLP), Speech Recognition.

4. Natural Language Processing (NLP)

• Overview:
  • Focuses on enabling machines to understand, interpret, and generate human language.
• Key Techniques:
  • Tokenization, Stopword Removal, Stemming, Lemmatization.
  • Sentiment Analysis, Machine Translation, Text Summarization.
• Advanced Models:
  • Transformers (e.g., BERT, GPT), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs).

5. Computer Vision

• Overview:
  • Enables machines to interpret visual data like images and videos.
• Techniques:
  • Image Processing: Filtering, Edge Detection.
  • Object Detection: YOLO, SSD, Faster R-CNN.
  • Facial Recognition and Optical Character Recognition (OCR).
• Applications:
  • Autonomous Vehicles, Medical Imaging, Augmented Reality.

6. Tools and Frameworks

• Programming Languages: Python, R, Julia.
• Libraries and Frameworks:
  • TensorFlow, PyTorch, Scikit-Learn, Keras, OpenCV.
• Cloud AI Services:
  • Google AI, AWS Machine Learning, Microsoft Azure AI.