recentpopularlog in


« earlier   
Differentiable Plasticity: A New Method for Learning to Learn | Uber Engineering Blog
Uber AI Labs has developed a new method called differentiable plasticity that lets us train the behavior of plastic connections through gradient descent so that they can help previously-trained networks adapt to future conditions. While evolving such plastic neural networks is a longstanding area of research in evolutionary computation, to our knowledge the work introduced here is the first to show it is possible to optimize plasticity itself through gradient descent. Because gradient-based methods underlie many of the recent spectacular breakthroughs in artificial intelligence (including image recognition, machine translation, Atari video games, and Go playing), making plastic networks amenable to gradient descent training may dramatically expand the power of both approaches.
ai  learning  machine-learning  ml 
14 hours ago by nico.ash
[1804.09170] Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and that performance can degrade substantially when the unlabeled dataset contains out-of-class examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.
machine-learning  semisupervised  evaluation 
16 hours ago by arsyed
Prodigy - Radically efficient machine teaching
An active learning-powered annotation tool for named entity recognition, text classification, object detection, image segmentation, A/B evaluation and more.
ai  machine-learning  nlp  tools 
23 hours ago by arobinski
[1712.05855] A Berkeley View of Systems Challenges for AI
"With the increasing commoditization of computer vision, speech recognition and machine translation systems and the widespread deployment of learning-based back-end technologies such as digital advertising and intelligent infrastructures, AI (Artificial Intelligence) has moved from research labs to production. These changes have been made possible by unprecedented levels of data and computation, by methodological advances in machine learning, by innovations in systems software and architectures, and by the broad accessibility of these technologies.
The next generation of AI systems promises to accelerate these developments and increasingly impact our lives via frequent interactions and making (often mission-critical) decisions on our behalf, often in highly personalized contexts. Realizing this promise, however, raises daunting challenges. In particular, we need AI systems that make timely and safe decisions in unpredictable environments, that are robust against sophisticated adversaries, and that can process ever increasing amounts of data across organizations and individuals without compromising confidentiality. These challenges will be exacerbated by the end of the Moore's Law, which will constrain the amount of data these technologies can store and process. In this paper, we propose several open research directions in systems, architectures, and security that can address these challenges and help unlock AI's potential to improve lives and society. "
michael.i.jordan  cs  ai  vision  quo-vadis  machine-learning  exploration 
yesterday by MarcK

Copy this bookmark:

to read