The program focused on the following four themes:
- Optimization: How and why can deep models be fit to observed (training) data?
- Generalization: Why do these trained models work well on similar but unobserved (test) data?
- Robustness: How can we analyze and improve the performance of these models when applied outside their intended conditions?
- Generative methods: How can deep learning be used to model probability distributions?
Welcome to the course blog for the Oxford first year Groups and Group Actions course (Hilary and Trinity Terms 2017). I hope that this will be a useful resource to accompany the lectures, problems sheets and tutorials. Please check back after each lecture for a new post. In addition, I have a course page with some useful information, and…
The textbook An Introduction to the Analysis of Algorithms by Robert Sedgewick and Phillipe Flajolet overviews the primary techniques used in the mathematical analysis of algorithms.
The textbook Analytic Combinatorics by Philippe Flajolet and Robert Sedgewick enables precise quantitative predictions of the properties of large combinatorial structures.
In an earlier post I mentioned that one goal of the new introductory curriculum at Carnegie Mellon is to teach parallelism as the general case of computing, rather than an esoteric, specialized subject for advanced students. Many people are incredulous when I tell them this, because it immediately conjures in their mind the myriad complexities…
The PUNLAG seminar is intended to supplement the numerical linear algebra course sequence at Purdue. The standard course CS515 doesn't have room for a number of interesting problems -- we hope to cover some in this seminar!
Learn AI from Stanford professors Christopher Manning, Andrew Ng, and Emma Brunskill. Free online course videos in Deep Learning, Reinforcement Learning, and Natural Language Processing.
This course will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN) and reinforcement learning. Application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation will be covered. High Performance Computing (HPC) aspects will demonstrate how deep learning can be leveraged both on graphical processing units (GPUs), as well as grids. Focus is primarily upon the application of deep learning to problems, with some introduction to mathematical foundations. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras.
- Modern C++ for Computer Vision
- 3D Coordinate Systems
- Photogrammetry I
- Mobile Sensing and Robotics I
- Photogrammetry II
- Mobile Sensing and Robotics II
- Techniques for Self-Driving Cars
- Master Project
This program aims to reunite researchers across disciplines that have played a role in developing the theory of reinforcement learning. It will review past developments and identify promising directions of research, with an emphasis on addressing existing open problems, ranging from the design of efficient, scalable algorithms for exploration to how to control learning and planning. It also aims to deepen the understanding of model-free vs. model-based learning and control, and the design of efficient methods to exploit structure and adapt to easier environments.