Master of Science in Artificial Intelligence

This course is designed to provide students with a comprehensive overview of the key concepts, techniques, and applications of AI. This course covers the history and evolution of AI, fundamental theories, and essential algorithms, including search methods, knowledge representation, machine learning, and neural networks. Students will explore the practical applications of AI in various domains such as robotics, natural language processing, computer vision, and expert systems, gaining an understanding of how AI technologies are transforming industries and society. Through a mix of theoretical lectures and hands-on exercises, students will develop a solid grounding in AI principles and practices. They will engage in projects and case studies that illustrate real-world AI applications, enhancing their problem-solving and critical-thinking skills. By the end of the course, students will have a thorough understanding of AI fundamentals and be prepared to delve deeper into specialised AI topics, positioning themselves for success in advanced courses and professional roles within the field of artificial intelligence.

This is a core and foundational course which aims to equip the student with the ability to model, design, implement and query relational database systems for real-world data storage & processing needs. Students would start with diagrammatic tools (ER-diagram) to map a real world data storage problem into entities, relationships and keys. Then, they learn to translate the ER-diagram into a relational model with tables. SQL is then introduced as a de facto tool to create, modify, append, delete, query and manipulate data in a relational database. Due to SQL’s popularity, the course spends considerable time building the ability to write optimized and complex queries for various data manipulation tasks. The module exposes students to various real world SQL examples to build solid practical knowledge. Students then move on to understanding various trade-offs in modern relational databases like the ones between storage space and latency. Designing a database would need a solid understanding of normal forms to minimize data duplication, indexing for speedup and flattening tables to avoid complex joins in low-latency environments. These real-world database design strategies are discussed with practical examples from various domains. Most of this course uses the opensource MySQL database and cloud-hosted relational databases (like Amazon RDS) to help students apply the concepts learned on real databases via assignments.

The ability to solve problems is a skill, and just like any other skill, the more one practices, the better one gets. So how exactly does one practice problem solving? Learning about different problem-solving strategies and when to use them will give a good start. Problem solving is a process. Most strategies provide steps that help you identify the problem and choose the best solution.

Building a toolbox of problem-solving strategies will improve problem solving skills. With practice, students will be able to recognize and choose among multiple strategies to find the most appropriate one to solve complex problems. The course will focus on developing problem-solving strategies such as abstraction, modularity, recursion, iteration, bisection, and exhaustive enumeration.

The course will also introduce arrays and some of their real-world applications, such as prefix sum, carry forward, subarrays, and 2-dimensional matrices. Examples will include industry-relevant problems and dive deeply into building their solutions with various approaches, recognizing each’s limitations (i.e when to use a data structure and when not to use a data structure).

By the end of this course a student can come up with the best strategy which can optimize both time and space complexities by choosing the best data structure suitable for a given problem.

This course focuses on building basic classification and regression models and understanding these models rigorously both with a mathematical and an applicative focus. The module starts with a basic introduction to high dimensional geometry of points, distance-metrics, hyperplanes and hyperspheres. We build on top this to introduce the mathematical formulation of logistic regression to find a separating hyperplane. Students learn to solve the optimization problem using vector calculus and gradient descent (GD) based algorithms. The module introduces computational variations of GD like mini-batch and stochastic gradient descent. Students also learn other popular classification and regression methods like k-Nearest Neighbours, Naive Bayes, Decision Trees, Linear Regression etc. Students also learn how each of these techniques under various real-world situations like the presence of outliers, imbalanced data, multi-class classification etc. Students learn bias and variance trade-off and various techniques to avoid overfitting and underfitting. Students also study these algorithms from a Bayesian viewpoint along with geometric intuition. This module is hands-on and students apply all these classical techniques to real-world problems.

This course provides a strong mathematical and applicative introduction to Deep Learning. The course starts with the perceptron model as an over-simplified approximation to a biological neuron. We motivate the need for a network of neurons and how they can be connected to form a Multi Layered Perceptron (MLPs). This is followed by a rigorous understanding of back-propagation algorithms and its limitations from the 1980s. Students study how modern deep learning took off with improved computational tools and data sets. We teach more modern activation units (like ReLU and SeLU) and how they overcome problems with the more classical Sigmoid and Tanh units. Students learn weight initialization methods, regularisation by dropouts, batch normalisation etc., to ensure that deep MLPs can be successfully trained. The course teaches variants of Gradient Descent that have been specifically designed to work well for deep learning systems like ADAM, AdaGrad, RMSProp, etc. Students also learn AutoEncoders, VAEs, and Word2Vec as unsupervised, encoding deep-learning architectures. We apply all of the foundational theory learned to various real-world problems using TensorFlow 2 and Keras. Students also understand how TensorFlow 2 works internally with specific focus on computational graph processing.

This is a course that focuses both on architectural design and practical hands-on learning of the most used cloud services. The module extensively uses Amazon Web Services (AWS) to show real-world code examples of various cloud services. It also covers the core concepts and architectures in a platform-agnostic manner so that students can easily translate these learnings to other cloud platforms (like Azure, GCP etc.). The course starts with virtualization and how virtualized compute instances are created and configured. Students also learn how to auto-scale applications using load balancers and build fault-tolerant applications across a geographically distributed cloud. As relational databases are widely used in most enterprises, students learn how to migrate and scale (both vertically and horizontally) these databases on the cloud while ensuring enterprise-grade security. Virtual private clouds enable us to create a logically isolated virtual network of computer resources. Students learn to set up a VPC using virtualized compute servers on AWS. The course also covers the basics of networking while setting up a VPC. Students learn of the architecture and practical aspects of distributed object storage and how it enables low-latency and high-availability data storage on the cloud.

This course is aimed at building a strong foundational knowledge of Data Analytics tools used extensively in the Data Science field. There are now powerful data visualisation tools used in the business analytics industry to process and visualise raw business data in a very presentable and understandable format. A good example is Tableau, used by all data analytics departments of companies and in data analytics companies in various fields for its ease of use and efficiency. Tableau uses relational databases, Online Analytical Processing Cubes, Spreadsheets, and cloud databases to generate graphical type visualisations.  The course starts with visualisations and moves to an in-depth look at the different chart and graph functions, calculations, mapping, and other functionality. Students will be taught quick table calculations, reference lines, different types of visualisations, bands and distributions, parameters, motion charts, trends and forecasting, formatting, stories, performance recording, and advanced mapping. At the end of this course, students will be prepared, if they desire, to earn such industry desktop certifications as a Tableau Desktop Specialist, a Tableau Certified Associate, or a Tableau Certified Professional.

This course introduces basic probability theory, statistical methods, and computational algorithms to perform mathematically rigorous data analysis. The course starts with basic foundational concepts of random variables, histograms, and various plots (PMF, PDF, and CDF). Students learn various popular discrete and continuous distributions like Bernoulli, Binomial, Poisson, Gaussian, Exponential, Pareto, log-normal, etc., both mathematically and from an applicative perspective. Students learn various measures like mean, median, percentiles, quantiles, variance, and interquartile range. Students learn the pros and cons of each metric and understand when and how to use them in practice. Students will learn conditional probability and Bayes' theorem in the applied context of real-world problems in medicine and healthcare. The module teaches the foundations of non-parametric statistics and applies them to solve problems using computational tools. Students learn various methods to determine correlations rigorously in data. This is followed by applied and mathematical understanding of the statistics underlying control-treatment (A/B) experiments and hypothesis testing. The module engages computation tools in modern statistics like Bootstrapping, Monte-Carlo methods, RANSAC, etc.

This course is designed to introduce students to the core concepts and methodologies of data science. This course covers a broad range of topics, including data collection, cleaning, and preprocessing, as well as statistical analysis, data visualisation, and exploratory data analysis. Students will learn how to apply various data science techniques to extract valuable insights from large datasets, empowering them to make data-driven decisions in diverse fields such as business, healthcare, and technology. Throughout the course, students will engage in practical exercises and projects that emphasise the application of data science principles to real-world problems. By working with actual datasets and using state-of-the-art tools and software, students will develop the skills necessary to analyse, interpret, and present data effectively. Upon completion of the course, students will have a strong foundation in data science, enabling them to leverage data to solve complex problems and drive innovation in their professional careers within the realm of artificial intelligence.

This course is designed to cultivate a deep understanding of algorithm design and analysis. This course focuses on the principles of algorithmic problem-solving, teaching students how to develop efficient and effective algorithms for a wide range of computational problems. Key topics include algorithmic strategies such as divide-and-conquer, dynamic programming, greedy algorithms, and graph algorithms, along with an emphasis on computational complexity and optimization techniques. Through a blend of theoretical instruction and practical exercises, students will learn to approach problems systematically and devise algorithms that are both correct and optimised for performance. The course includes hands-on projects that challenge students to apply algorithmic thinking to real-world AI problems, enhancing their analytical and coding skills. By the end of the course, students will be equipped with the skills to design, implement, and evaluate algorithms, preparing them for advanced AI coursework and professional roles that require robust problem-solving abilities.

This course is dedicated to exploring the ethical, legal, and social implications of artificial intelligence technologies. This course examines key issues such as bias in AI algorithms, data privacy, transparency, accountability, and the impact of AI on employment and society. Students will engage with case studies and frameworks designed to address these challenges, learning how to develop and implement AI systems that align with ethical standards and promote fairness and inclusivity. Through a combination of theoretical discussions and practical applications, the course equips students with the knowledge and tools necessary to navigate the complex landscape of AI ethics. Students will participate in discussions on policy, regulations, and best practices, and will work on projects that involve designing ethical AI solutions and conducting impact assessments. By the end of the course, students will be prepared to advocate for and implement ethical AI practices in their professional roles, ensuring that AI technologies are developed and used responsibly and equitably.

This course is dedicated to mastering the art and science of designing effective prompts for large language models (LLMs). This course explores the principles of crafting precise and impactful prompts that elicit desired responses from advanced AI models such as GPT-3, BERT, and their successors. Students will learn various strategies for prompt construction, including techniques for optimising clarity, context, and specificity to enhance model performance in tasks like text generation, translation, and summarization.

Through a combination of theoretical insights and practical exercises, students will gain hands-on experience in developing and refining prompts to solve real-world problems. The course includes case studies and projects that demonstrate how prompt engineering can be applied across different domains, such as customer service, content creation, and data analysis. By the end of the course, students will be adept at leveraging prompt engineering to harness the full potential of large language models, enabling them to drive innovation and efficiency in their professional endeavours with AI.

This course gives the detailed overview on how to approach Low Level Design problems with real-world case studies discussed such as Designing a Pen (Mac/Windows), TicTacToe, BookMyShow (most used event booking app, manages millions of users), Email campaign Management System and detailed design of Splitwise.

This course is focused on the techniques and technologies that enable computers to understand, interpret, and generate human language. This course covers foundational topics in NLP, including tokenization, part-of-speech tagging, named entity recognition, and sentiment analysis. Students will explore advanced methods such as word embeddings, sequence-to-sequence models, and transformers, which are essential for applications like language translation, chatbots, and text summarization. Combining theoretical insights with practical implementation, the course includes hands-on projects and case studies that apply NLP techniques to real-world datasets. Students will gain experience using popular NLP libraries and frameworks, such as NLTK, SpaCy, and Hugging Face Transformers, to develop and refine language models. By the end of the course, students will be well-prepared to build and deploy sophisticated NLP solutions, enhancing their ability to work with and analyse textual data in various professional and research contexts.

This course helps students translate mathematical/statistical/scientific concepts into code. This is a foundational course for writing code to solve Data Science, ML & AI problems. It introduces basic programming concepts (like control structures, recursion, classes, and objects) from scratch, assuming no prerequisites, to make this course accessible to students from non-computational scientific fields like Biology, Physics, Medicine, Chemistry, Civil & Mechanical Engineering etc. After building a strong foundation, the course advances to dive deep into core Mathematical libraries like NumPy, Scipy, and Pandas. Students also learn when and how to use inbuilt-data structures like Lists, Dicts, Sets and Tuples. The module introduces the concepts of computational complexity to help students write optimised code using appropriate data structures and algorithmic design methods. The module does not dive deep into the data structures and algorithm design methods in this course – that is available in the ‘Data Structures and Algorithms’ module. This course is valuable for all students specialising in mathematical sub-areas of CS like ML, Data Science, Scientific Computing etc.

This is a project-based course, with the aim of building the required skills for creating web-based software systems. The course covers the entire lifecycle of building software projects, from requirement gathering and scope definition from a product document, to designing the architecture of the system, and all the way to delivery and maintenance of the software system.

The course covers both frontend, which is, building browser-based interfaces for users, using frontend web frameworks, and also building the backend, which is the server running an API to serve the information to the frontend, and running on an SQL or similar database management system for storage.

All aspects of delivering a software project, including security, user authentication and authorisation, monitoring and analytics, and maintaining the project are covered. The course also covers the aspects of project maintenance, like using a version control system, setting up continuous integration and deployment pipelines and bug trackers.

This course will focus on the principles and techniques involved in training large language models (LLMs). This course provides an in-depth understanding of the architectures and training methodologies used to develop powerful language models like GPT-3, BERT, and their successors. Students will explore the complexities of model training, including data preprocessing, tokenization, model architecture design, and fine-tuning. Emphasis will be placed on understanding the computational resources and optimization strategies required to train LLMs effectively. Throughout the course, students will engage in hands-on projects that involve training and fine-tuning LLMs on diverse datasets, gaining practical experience with tools and frameworks such as TensorFlow and PyTorch. Case studies will illustrate the application of LLMs in natural language processing tasks, such as text generation, translation, summarization, and question answering. By the end of the course, students will be equipped with the knowledge and skills to train large language models, enabling them to contribute to the development of state-of-the-art AI systems that leverage advanced language understanding and generation capabilities.