AI In Action
AI in Action: Developing Intelligent Systems from Scratch
Duration: 6-7 weeks
Week 1: Introduction to AI and Intelligent Systems
- Overview of Artificial Intelligence (AI)
- Definition, history, and types of AI
- Key concepts: Machine Learning, Deep Learning, Neural Networks
- Applications of AI
- Real-world applications in healthcare, finance, robotics
- AI in daily life: Virtual assistants, recommendation systems
- Setting Up Development Environment
- Installing Python, Jupyter Notebook, AI libraries
Week 2: Foundations of Machine Learning
- Introduction to Machine Learning
- Types of machine learning
- Core algorithms: Linear regression, decision trees
- Data Preprocessing
- Data cleaning, handling missing values
- Feature scaling and engineering
- Practical Implementation
- Implementing basic ML models using Scikit-learn.
Week 3: Building Neural Networks
- Introduction to Neural Networks
- Basic architecture: Neurons, layers, weights, activation functions.
- Understanding feedforward neural networks and backpropagation.
- Hands-on Project
- Creating a neural network for a classification task (e.g., handwritten digit recognition).
Week 4: Natural Language Processing
- Introduction to NLP
- What is NLP and how it’s used in AI applications.
- Text processing techniques: Tokenization, stemming, lemmatization.
- Building NLP Models
- Implementing simple NLP tasks: Sentiment analysis, text classification, chatbots.
- Tools for NLP: Using libraries like NLTK, spaCy.
- Practical Application
- Building a simple text classification model (e.g., spam detection).
Week 5: Computer Vision and Image Processing
- Introduction to Computer Vision
- Basics of image processing: Grayscale conversion, edge detection, and image filtering.
- Image classification, object detection, and segmentation.
- Deep Learning for Vision
- Convolutional Neural Networks (CNNs) for image recognition.
- Working with libraries like OpenCV, TensorFlow/Keras.
- Hands-on Project
- Image classification using a pre-trained CNN model.
Week 6: Reinforcement Learning (RL)
- Introduction to Reinforcement Learning
- Core concepts: Agents, environments, rewards, states, actions.
- Algorithms: Q-learning, policy gradients, and deep Q-networks (DQN).
- Developing RL Agents
- Implementing a simple RL agent to play games (e.g., Tic-Tac-Toe or CartPole)
- Practical Application
- Understanding how RL is used in real-world applications like robotics and gaming.
Week 7: AI Ethics and Responsible AI Development
- Ethical Implications of AI
- Bias in AI systems: Understanding and mitigating bias.
- Ethical challenges: Privacy, fairness, accountability, and transparency.
- Responsible AI Development
- Ensuring fairness in AI models.
- Best practices for ethical AI development.
- Capstone Project
- Developing a final AI-based system using concepts learned throughout the course.
- Students work on a project (e.g., AI-powered recommendation system, chatbot, or image classifier) and showcase their results.
₹55,999/-
₹17,999/-
