Curriculum

General Courses for AI Master/PhD

Artificial Intelligence: Principles and Techniques

Artificial Intelligence has emerged as an increasingly impactful discipline in science and technology. AI applications are embedded in the infrastructure of many products and industries search engines, medical diagnoses, speech recognition, robot control, web search, advertising and even toys. This introductory course provides a broad overview of modern artificial intelligence. Learn how machines can engage in problem solving, reasoning, learning, and interaction. Design, test and implement algorithms. Gain an appreciation of this dynamic field. 

Topics Include

  • Search

  • Constraint satisfaction

  • Markov decision processes

  • Planning and game playing

  • Machine learning

  • Graphical models

  • Logic

AI and Decision Making ​

This course is designed to increase awareness and appreciation for why uncertainty matters, particularly for aerospace applications. Introduces decision making under uncertainty from a computational perspective and provides an overview of the necessary tools for building autonomous and decision-support systems. Following an introduction to probabilistic models and decision theory, the course will cover computational methods for solving decision problems with stochastic dynamics, model uncertainty, and imperfect state information. Applications cover: air traffic control, aviation surveillance systems, autonomous vehicles, and robotic planetary exploration.

 

Topics Include

  • Bayesian networks

  • Influence diagrams

  • Dynamic programming

  • Reinforcement learning

  • Partially observable Markov decision processes

Machine Learning

Computers are becoming smarter, as artificial intelligence and machine learning, a subset of AI, make tremendous strides in simulating human thinking. Creating computer systems that automatically improve with experience has many applications including robotic control, data mining, autonomous navigation, and bioinformatics.  This course provides a broad introduction to machine learning and statistical pattern recognition. Learn about both supervised and unsupervised learning as well as learning theory, reinforcement learning and control. Explore recent applications of machine learning and design and develop algorithms for machines.

Topics Include

  • Basics concepts of machine learning

  • Generative learning algorithms

  • Evaluating and debugging learning algorithms

  • Bias/variance tradeoff and VC dimension

  • Value and policy iteration

  • Q-learning and value function approximation

Deep Learning​

Deep Learning is one of the most highly sought after skills in AI. We will help you become good at Deep Learning. In this course, you will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to lead successful machine learning projects. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. You will work on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. You will master not only the theory, but also see how it is applied in industry. You will practice all these ideas in Python and in TensorFlow, which we will teach. After this course, you will likely find creative ways to apply it to your work. This class is taught in the flipped-classroom format. You will watch videos and complete in-depth programming assignments and online quizzes at home, then come to class for advanced discussions and work on projects. This class will culminate in an open-ended final project, which the teaching team will help you on.

Topics Include

  • Foundations of neural networks and deep learning

  • Techniques to improve neural networks: regularization and optimizations, hyperparameter tuning and deep learning frameworks (Tensorflow and Keras.)

  • Strategies to organize and successfully build a machine learning project

  • Convolutional Neural Networks, its applications (object classification, object detection, face verification, style transfer …) and related methods

  • Recurrent Neural Networks, its applications (natural language processing, speech recognition, …) and related methods

  • Advanced topics: Generative Adversarial Networks, Deep Reinforcement Learning, Adversarial Attacks

  • Insights from the AI industry, from academia, and advice to pursue a career in AI

Cognitive Psychology

Why are people smarter than machines? This course explores how the study of human intelligence can inform and improve artificial intelligence. We will look to cognitive science, with special focus on cognitive development, to help elucidate a set of “key ingredients” that are important components of human learning and thought, but are either underutilized or absent in contemporary artificial intelligence. Through readings and discussion, we will cover ingredients such as “intuitive physics,” “intuitive psychology,” “compositionality,” “causality,” and “learning-to-learn,” although students will be encouraged to contribute other ingredients. Each ingredient will be discussed and compared from the perspectives of both cognitive science and AI, with readings drawn from both fields with roughly a 50/50 proportion.

Topics Include

  • Deep learning

  • Intuitive physics (part 1: humans)

  • Intuitive physics (part 2: machines)

  • Intuitive psychology (part 1: humans)

  • Intuitive psychology (part 2: machines)

  • Compositionality

  • Causality

  • Critiques of “Building machines that learn and think like people”

  • Language and Culture

  • Emotion and Egocentric learning

Social analytics and Applications

This course is designed to study the methods for the analysis of social networks from graph mining techniques. The this module, you will learn about

1. Python programming and build crawlers to get data from social network

2. Processing and analysing data from various social networks

3. Social influence, social links, ego networks 

Topics Include

  • Graph theory 

  • Google analytics

  • Network analysis 

  • Modelling and visualisations

Special Courses for AI Master/PhD (Computing)

Special Courses for AI Master/PhD (Cognitive Psychology)

Computational Logics

This course is a rigorous introduction to Logic from a computational perspective. It shows how to encode information in the form of logical sentences; it shows how to reason with information in this form; and it provides an overview of logic technology and its applications - in mathematics, science, engineering, business, law, and so forth. Topics include the syntax and semantics of Propositional Logic, Relational Logic, and Herbrand Logic, validity, contingency, unsatisfiability, logical equivalence, entailment, consistency, natural deduction (Fitch), mathematical induction, resolution, compactness, soundness, completeness.

Natural Language Processing

Investigate the fundamental concepts and ideas in natural language processing (NLP), and get up to speed with current research. Students will develop an in-depth understanding of both the algorithms available for processing linguistic information and the underlying computational properties of natural languages. The focus is on deep learning approaches: implementing, training, debugging, and extending neural network models for a variety of language understanding tasks. The course progresses from word-level and syntactic processing to question answering and machine translation. For their final project students will apply a complex neural network model to a large-scale NLP problem.

Topics Include

  • Computational properties of natural languages

  • Coreference, question answering, and machine translation

  • Processing linguistic information

  • Syntactic and semantic processing

  • Modern quantitative techniques in NLP

  • Neural network models for language understanding tasks

Artificial General Intelligence and Cognitive Architecture​

Deep learning has achieved remarkable success in supervised and reinforcement learning problems including image classification, speech recognition, and game playing. These models are, however, to a large degree, specialized for the single task they are trained for. This course will cover the setting where there are multiple tasks to be solved. You will explore goal-conditioned reinforcement learning techniques that can increase learning speed of multiple tasks. You will discover how meta-learning methods can be used to learn new tasks quickly. You will learn how leverage the shared structure of a sequence of tasks to enable knowledge transfer. Through this course, you will develop and advance highly-sought after skills in the field of AI.

Topics Include

  • Multi-Task Supervised Learning

  • Bayesian Models and Deep Probabilistic Meta-Learning Approaches

  • Model-Based Reinforcement Learning for Multi-Task Learning

  • Learning Optimizers, Learning Rules, and Architectures

Neuroscience

This course explores the problem of intelligence?its nature, how it is produced by the brain and how it could be replicated in machines?using an approach that integrates cognitive science, which studies the mind; neuroscience, which studies the brain; and computer science and artificial intelligence, which study the computations needed to develop intelligent machines.

Topics Include

  • Neural circuits of intelligence 

  • Modelling human cognition

  • Development of intelligence

  • Visual intelligence

  • Vision and language

  • Social intelligence

  • Audition and Speech

  • Robotics

  • Theory of intelligence

Special Courses for AI Master/PhD (Arts Technology - Human-Computer Interaction)

Multisensory Integration

Will be updated​

Big Data and Scientific illustration

Will be updated​

Sound Design

Will be updated​

3D VR Design

Will be updated​

Probabilistic Models: Principles and Techniques​

Learn important probabilistic modeling languages for representing complex domains and how the graphic models extend to decision making. Use ideas from discrete data structures in computer science to efficiently encode and manipulate probability distributions over high-dimensional spaces. Apply the basics of the Probabilistic Graphical Model representation and learn how to construct them, using both human knowledge and machine learning techniques to reach conclusions and make good decisions under uncertainty.

Topics Include

  • Bayesian and Markov networks

  • Exact and approximate probabilistic inference algorithms

  • Speech recognition

  • Biological modeling and discovery

  • Message encoding

  • Medical diagnosis

  • Robot motion planning

Symbolic AI and Expert Systems 

The objective of this course is to provide the student with an overview of topics in the field of artificial intelligence (AI). The course also provides the student with a working knowledge of designing an expert system and applying expert system technology in designing and analyzing engineering systems. The first part of the course covers historical background, knowledge acquisition and knowledge representation including propositional calculus, predicate calculus, semantic networks, frame systems and production rules. Various search techniques will be discussed. Fuzzy logic systems, neural network systems and computer vision systems will be briefly discussed in the second part of the course. The third part of this course will be devoted to the design of expert systems. Applications of expert systems in engineering system design and analysis will be stressed throughout. Case studies will be discussed. Class project is required. Students are encouraged to design expert systems for his/her own engineering applications.

Topics Include

  • Knowledge Representation (5 classes)

  • Methods of Inference (1 class)

  • Search Techniques (3 classes)

  • Fuzzy Logic Systems (3 classes)

  • Neural Network (3 classes)

  • Pattern Recognition and Computer Vision (3 classes)

  • Expert Systems (6 classes)

  • Languages For AI Problem Solving 

Convolutional Neural Networks for Visual Recognition​

Computer Vision is a dynamic and rapidly growing field with countless high-profile applications that have been developed in recent years. The potential uses are diverse, and its integration with cutting edge research has already been validated with self-driving cars, facial recognition, 3D reconstructions, photo search and augmented reality. Artificial Intelligence has become a fundamental component of everyday technology, and visual recognition is a key aspect of that.  It is a valuable tool for interpreting the wealth of visual data that surrounds us and on a scale impossible with natural vision. This course covers the tasks and systems at the core of visual recognition with a detailed exploration of deep learning architectures. While there will be a brief introduction to computer vision and frameworks, such as Caffe, Torch, Theano and TensorFlow, the focus will be learning end-to-end models, particularly for image classification. Students will learn to implement, train and debug their own neural networks as well as gain a detailed understanding of cutting-edge research in computer vision. 

Topics Include

  • End-to-end models

  • Image classification, localization and detection

  • Implementation, training and debugging

  • Learning algorithms, such as backpropagation

  • Long Short Term Memory (LSTM)

  • Recurrent Neural Networks (RNN)

  • Supervised and unsupervised learning

Reinforcement Learning​

Reinforcement Learning (RL) provides a powerful paradigm for artificial intelligence and the enabling of autonomous systems to learn to make good decisions. RL is relevant to an enormous range of tasks, including robotics, game playing, consumer modeling and healthcare. This class will provide a solid introduction to the field of RL. Students will learn about the core challenges and approaches in the field, including generalization and exploration. Through a combination of lectures, and written and coding assignments, students will become well-versed in key ideas and techniques for RL. Assignments will include the basics of reinforcement learning as well as deep reinforcement learning-- an extremely promising new area that combines deep learning techniques with reinforcement learning. In addition, students will advance their understanding and the field of RL through an open-ended project. 

Topics Include

  • Key features of RL

  • Policy iteration, TD learning and Q-learning

  • Linear value approximation

  • MDP, POMDP, bandit, batch offline and online RL

  • RL algorithms

  • Open challenges and hot topics in RL