The course will cover techniques to compute on encrypted data, particularly homomorphic encryption, both partial homomorphic encryption, and fully homomorphic encryption. The course will have a large theory component. However, it will also discuss how homomorphic encryption is applied to real systems such as databases, media streaming services, anonymous messaging services, and machine learning systems.
Course information: this course covers the fundamentals of quantum computation as well as some advanced topics including quantum information theory, algorithms and cryptography. Necessary math prerequisites: linear algebra and probability. Mathematical maturity is a must.
Have you ever used intelligent virtual assistants such as OpenAI ChatGPT, Google Now, Apple Siri, Amazon Alexa or Microsoft Cortana? What are the technologies behind such systems? How did IBM's Watson beat top human Jeopardy players? Or are you just curious about how Google Translate works? Understanding human language is an important goal for Artificial Intelligence, and this course introduces fundamental theories and practical applications in Natural Language Processing (NLP).
Haptics lies at the intersection of robotics, human-computer interaction, and computational and human perception. The term "haptics" is often used to refer to science and engineering related to the sense of touch. This course introduces human haptics, including sensory specializations and touch perception. It reviews the engineering of electronic technologies for haptic (touch) feedback, emerging technologies, and the design of haptic systems for human-computer interaction, sensory substitution, virtual reality, augmented reality, and other emerging areas.
This is a graduate-level research course on deep learning. We will discuss/present the newest and important publications in deep learning, specifically Transformer-based techniques in the areas of knowledge base, question answering, conversational AI, natural language processing and multimodal learning.
Deep neural networks have achieved remarkable success owing to their superior predictive performance. Yet, they are extremely vulnerable to adversarial attacks. This makes adversarial machine learning an emerging topic. The idea of learning with adversaries is crucial for expanding the learning capability, ensuring trustworthy decision-making, and enhancing the generalizability of AI models. Despite diverse adversarial concepts and applications, they share very similar learning, computation, and optimization foundations.
One of the perennial goals of Computer Graphics is creating high quality images which are indistinguishable from photographs: a goal referred to as photorealism. Another important goal is interactivity for visualization, simulation, gaming and other real-time applications. These two goals have historically been at odds with each other.
The goal of the class is to learn the basics of probability theory, how to reason rigorously about probability, to learn concentration inequalities (Markov, Chebyshev, Chernoff, ++) and know to apply those in the context of algorithm analysis and design.
Textbook: Randomized Algorithms by Mitzenmaher and Upfal (Second Edition). We will cover approximately the 7 first chapters, plus possibly additional readings. The precise syllabus will develop as we go along! See Q&A Lecture Schedule post for the approximate schedule.
Deep Learning has been driving the progress of AI in the past decade and has found versatile applications in many products and everyday life. Examples include recommendation systems for online videos, automatic language translation, smart home assistants, and autonomous driving vehicles. This course will introduce general principles, methods, network architectures, and applications of Deep Learning. We cover neural network architectures including convolutional neural networks, recurrent neural networks, Transformer, and graph neural networks.