Local online learning in recurrent networks with random feedback
نویسندگان
چکیده
منابع مشابه
Online Learning with Local Permutations and Delayed Feedback
We propose an Online Learning with Local Permutations (OLLP) setting, in which the learner is allowed to slightly permute the order of the loss functions generated by an adversary. On one hand, this models natural situations where the exact order of the learner’s responses is not crucial, and on the other hand, might allow better learning and regret performance, by mitigating highly adversarial...
متن کاملOnline Learning with Partial Feedback
In previous lectures we talked about the general framework of online convex optimization and derived an algorithm for prediction with expert advice from this general framework. To apply the online algorithm, we need to know the gradient of the loss function at the end of each round. In the prediction of expert advice setting, this boils down to knowing the cost of each individual expert. In thi...
متن کاملOnline Learning with Preference Feedback
We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback (e.g. clicks). In particular, at each time step a potentially structured object (e.g. a ranking) is presented to the user in response to a context (e.g. query)...
متن کاملLocal learning rules and bifurcations in the global dynamics of random recurrent neural networks∗
In this article, we investigate the effects of biologically-plausible local learning rules (Hebbian rules) on the global dynamics of firing-rate random recurrent neural networks. In these models, learning collapses the initially chaotic dynamics onto simpler attractors (limit cycle or fixed point) that are specific of the learned pattern. This phenomenon provides these networks with associative...
متن کاملOnline Learning with Random Representations
We consider the requirements of online learning—learning which must be done incrementally and in realtime, with the results of learning available soon after each new example is acquired. Despite the abundance of methods for learning from examples, there are few that can be used effectively for online learning, e.g., as components of reinforcement learning systems. Most of these few, including r...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: eLife
سال: 2019
ISSN: 2050-084X
DOI: 10.7554/elife.43299