Join today and earn 25 RSC
What is ResearchCoin?

Trending Papers in machine learning

Fast reinforcement learning with generalized policy updates
Published: Aug 2020
  • The generalized version of policy improvement and policy evaluation allows one to leverage the solution of some tasks to speed up the solution of others. If the reward function of a task can be well approximated as a linear combination of the reward functions of tasks previously solved, we can reduce a reinforcement-learning problem to a simpler linear regression. When this is not the case, the agent can still exploit the task solutions by using them to interact with and learn about the environment. Both strategies considerably reduce the amount of data needed to solve a reinforcement-learning problem.
  • The combination of reinforcement learning with deep learning is a promising approach to tackle important sequential decisionmaking problems that are currently intractable. One obstacle to overcome is the amount of data needed by learning systems of this type. This article proposes to address this issue through a divide-and-conquer approach. The authors argue that complex decision problems can be naturally decomposed into multiple tasks that unfold in sequence or in parallel. By associating each task with a reward function, this problem decomposition can be seamlessly accommodated through a generalization of two fundamental operations in reinforcement learning: policy improvement and policy evaluation.
Submitted by Sebastian Hunte
Slide 1 of 1
Real-Time Sign Language Detection using Human Pose Estimation
Published: Aug 2020
  • The end result is a demo application for sign language detection in the browser in order to demonstrate its usage possibility in videoconferencing applications
  • The authors extract optical flow features based on human pose estimation and, using a linear classifier, show these features are meaningful with an accuracy of 80%, evaluated on the DGS Corpus
Submitted by Lex Bouter
Slide 1 of 1
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
Tenney, Ian, et al
Published: Aug 2020
  • LIT makes explanability easily accessible for researchers and practitioners alike.
  • LIT's analysis covers "local explanations" like attention and "aggregate analysis" like accuracy. It also allows users to run counterfactuals live.
Submitted by Tim Dingman
Slide 1 of 1
Better prediction of drug treatments using machine learning and public data sets
Published: Sep 2017
  • An algorithm can predict whether a drugs treats a disease by looking at the types of network paths in between.
  • Biomedical knowledge can be represented using a network with multiple types of nodes and edges.
Submitted by Daniel Himmelstein
Slide 1 of 1
Slide 1 of 1
Do Adversarially Robust ImageNet Models Transfer Better?
  • Adversarially robust models also improve with increasing width, whereas the opposite trend holds for standard models
  • Adversarially robust models underperform compared to standard models on training data, but overperform in transfer learning
Submitted by Tim Dingman
Slide 1 of 1
OpenAI's natural language processing model, GPT-3, has 175 billion parameters, can translate, question/answer, write poems, and read conceptual tasks, all without fine-tuning
From Paper: Language Models are Few-Shot Learners
Published: Jun 2020
  • These results suggest that very large language models may be an important ingredient in the development of adaptable, general language systems
  • Around 80 US-based participants were presented with a quiz consisting of real titles and subtitles followed by either the human-written article or the article generated by the model4
Submitted by Angela Meng
Slide 1 of 1
Forecasting Bitcoin closing price series using linear regression and neural networks models
In this article we forecast daily closing price series of Bitcoin, Litecoin and Ethereum cryptocurrencies, using data on prices and volumes of prior days. Cryptocurrencies price behaviour is still largely unexplored, presenting new opportunities for researchers and economists to highlight similarities and differences with standard financial prices. We compared our results with various benchmarks: one recent work on Bitcoin prices forecasting that follows different approaches, a well-known paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval and another, more recent paper which gives quantitative results on stock market index predictions. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms: the Simple Linear Regression (SLR) model for uni-variate series forecast using only closing prices, and the Multiple Linear Regression (MLR) model for multivariate series using both price and volume data. We used two artificial neural networks as well: Multilayer Perceptron (MLP) and Long short-term memory (LSTM). While the entire time series resulted to be indistinguishable from a random walk, the partitioning of datasets into shorter sequences, representing different price ‘‘regimes’’, allows to obtain precise forecast as evaluated in terms of Mean Absolute Percentage Error(MAPE) and relative Root Mean Square Error (relativeRMSE). In this case the best results are obtained using more than one previous price, thus confirming the existence of time regimes different from random walks. Our models perform well also in terms of time complexity, and provide overall results better than those obtained in the benchmark studies, improving the state-of-the-art.
Submitted by Patrick Joyce
Slide 1 of 1
A distributional code for value in dopamine-based reinforcement learning
Published: Jan 2019
  • The key difference in distributional reinforcement learning (RL) lies in how ‘anticipated reward’ is defined. In traditional RL, the reward prediction is represented as a single quantity: the average taken over all potential reward outcomes, weighted by their respective probabilities. By contrast, distributional RL uses a multiplicity of predictions. These predictions vary in their degree of optimism about upcoming reward. More optimistic predictions anticipate obtaining greater future rewards; less optimistic predictions anticipate less positive outcomes. Together, the entire range of predictions captures the full probability distribution over future rewards.
  • A person's mood has been linked with predictions of future reward and it has been proposed that both depression and bipolar disorder may involve biased predictions of future value. These biases may arise from asymmetries in reward prediction error (RPE) coding.
Submitted by Sebastian Hunte
Slide 1 of 1
A deep learning framework for neuroscience
  • Much of systems neuroscience has attempted to formulate succinct statements about the function of individual neurons in the brain. This approach has been successful at explaining some (relatively small) circuits and certain hard-wired behaviours. However, there is reason to believe that this approach will need to be complemented by other insights if we are to develop good models of plastic circuits with thousands, millions or billions of neurons. There is, unfortunately, no guarantee that the function of individual neurons in the CNS can be compressed down to a human-interpretable, verbally articulable form. Given that we currently have no good means of distilling the function of individual units in deep ANNs into words, and given that real brains are likely more, not less, complex, we suggest that systems neuroscience would benefit from focusing on the kinds of models that have been successful in ANN research programs, i.e., models grounded in the three essential components: objective functions, the learning rules and the architectures.
  • a lot of computational neuroscience has emphasized models of the dynamics of neural activity, which has not been a major theme in this discussion. As such, one might worry that the framework fails to connect with this past literature.
Submitted by Sebastian Hunte
Slide 1 of 1
Load More Papers

Most Reputable Users

Tim Dingman
Lex Bouter
Patrick Joyce
Anton Popov
Sebastian Hunte
Елена Белоснежная
Daniel Himmelstein
Angela Meng
Rafael Baptista
Andy Tertychniy