The purpose of AI Magazine is to disseminate timely and informative articles that represent the current state of the art in AI and to keep its readers posted on AAAI-related matters. The articles are selected for appeal to readers engaged in research and
My name is Daniel Holden. I'm a researcher at Ubisoft Montreal using Machine Learning for character animation and other applications. I'm also a Digital Artist and Writer. My interests are Computer Graphics, Game Development, Theory of Computation, and Programming Languages.
Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications. Active learning aims at red
Download Open Datasets on 1000s of Projects + Share Projects on One Platform. Explore Popular Topics Like Government, Sports, Medicine, Fintech, Food, More. Flexible Data Ingestion.
Turning procedural and structural knowledge into programs has established methodologies, but what about turning knowledge into probabilistic models? I explore a few examples of what such a process could look like.
While deep learning has achieved remarkable success in supervised and reinforcement learning problems, such as image classification, speech recognition, and game playing, these models are, 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, and study how the structure arising from multiple tasks can be leveraged to learn more efficiently or effectively. This includes:
- goal-conditioned reinforcement learning techniques that leverage the structure of the provided goal space to learn many tasks significantly faster
- meta-learning methods that aim to learn efficient learning algorithms that can learn new tasks quickly
- curriculum and lifelong learning, where the problem requires learning a sequence of tasks, leveraging their shared structure to enable knowledge transfer
This is a graduate-level course. By the end of the course, students will be able to understand and implement the state-of-the-art multi-task learning and meta-learning algorithms and be ready to conduct research on these topics.
Unlike task-specific algorithms, Deep Learning is a part of Machine Learning family based on learning data representations. With massive amounts of computational power, machines can now recognize…
This year was huge for me in the field of machine learning and computer vision in particular. A bit more than a year ago I would never believe that I would spend a week abroad not…
All AI/Machine learning jobs in one place. Machine learning jobs; remote, on location, interesting companies, and a directory of developers that work with machine learning
This post discusses the benefits of full-stack data science generalists over narrow functional specialists. The later will help you execute and bring process...
- ARM Research
- Hound: Causal Learning for Datacenter-scale Straggler Diagnosis
- Adaptive Resource Management for Mobile CMPs through Self-awareness
- On-the-fly deterministic binary filters and other on-going work in Machine Learning Systems
- Managed Modularity for Deep Neural Networks
Have you ever wondered how will the machine learning frameworks of the '20s look like? In this essay, I examine the directions AI research might take and the requirements they impose on the tools at our disposal, concluding with an overview of what I believe to be the two strong candidates: `JAX` and `S4TF`.
A. Alemi, and I. Fischer. (2018)cite arxiv:1807.04162Comment: Presented at the ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models.
M. Lindvall, and J. Molin. (2020)cite arxiv:2001.07455Comment: Accepted for presentation in poster format for the ACM CHI'19 Workshop <Emerging Perspectives in Human-Centered Machine Learning>.