What is Artificial Intelligence?
Artificial Intelligence (AI) is one of the most transformative and rapidly evolving fields in modern technology. At its core, AI refers to the simulation of human intelligence processes by computer systems. These processes include learning, reasoning, problem-solving, perception, understanding natural language, and decision-making. Rather than being explicitly programmed with a fixed set of rules for every situation, AI systems are designed to adapt, improve, and make intelligent decisions based on data and experience.
AI systems work by processing large volumes of data, identifying patterns within that data, and using those patterns to make predictions or decisions.
The learning objectives of this course are:
- To understand Generative AI and Large Language Models (LLMs) and their agents.
- To learn Natural Language Processing (NLP) and its applications.
- To understand Generative Adversarial Networks (GANs) and how they generate synthetic data.
- To learn Retrieval-Augmented Generation (RAG) for enhancing AI responses with external knowledge.
- To explore Agentic AI and autonomous AI systems.
- To work with AI tools such as Cursor AI, GitHub Copilot, and Claude.
- To integrate and build applications using OpenAI APIs.
What is Machine Learning?
Machine Learning is the field of study that gives computers the capability to learn without being explicitly programmed. ML is one of the most exciting technologies that one has ever come across. As it is evident from the name, it gives the computer something that makes it more similar to humans: The ability to learn. Machine learning is actively being used today, perhaps in many more places than one would expect.
The learning objectives of this course are:
- To understand the concept of supervised learning and apply classification and regression techniques.
- To learn and implement key ML algorithms — Linear Regression, Logistic Regression, Naive Bayes, KNN, and Decision Trees.
- To understand unsupervised learning and apply clustering algorithms such as K-Means and DBSCAN.
- To learn dimensionality reduction using PCA.
- To understand reinforcement learning and its real-world applications.
- To evaluate ML models using precision, recall, F1 score, and the bias/variance tradeoff.
- To gain hands-on experience using Scikit-learn and Kaggle.
- To understand neural networks, their architecture, and key terminologies.
- To learn forward and backward propagation and the role of the perceptron.
- To design and implement Feedforward Neural Networks (FNN).
- To understand Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks and their advantages.
- To learn Convolutional Neural Networks (CNN) for image-based tasks.
- To understand the Transformer architecture and its impact on modern AI.
- To work with PyTorch and compare it with TensorFlow and Keras.
- To understand and apply statistics and probability concepts used in AI model building.
- To learn linear algebra and calculus as the mathematical foundation for machine learning algorithms.
- To understand the Central Limit Theorem and its significance in data analysis.
