Home /
Research
Showing 109 - 114 / 897
Learning efficient task-dependent representations with synaptic plasticity
ColinBredenberg, EeroSimoncelli, CristinaSavin....
Published date-12/01/2020
Neural populations encode the sensory world imperfectly: their capacity is limited by the number of neurons, availability of metabolic and other biophysical resources, and intrinsic noise. The brain is presumably …
Learning Disentangled Representations and Group Structure of Dynamical Environments
RobinQuessard, ThomasBarrett, WilliamClements....
Published date-12/01/2020
Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe …
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
ZixuanKe, BingLiu, XingchangHuang....
Published date-12/01/2020
ContinualLearning, TransferLearning
Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some …
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds
ValentinLiévin, AndreaDittadi, AndersChristensen....
Published date-12/01/2020
This paper introduces novel results for the score-function gradient estimator of the importance-weighted variational bound (IWAE). We prove that in the limit of large $K$ (number of importance samples) one …
High-Dimensional Contextual Policy Search with Unknown Context Rewards using Bayesian Optimization
QingFeng, BenLetham, HongziMao....
Published date-12/01/2020
Contextual policies are used in many settings to customize system parameters and actions to the specifics of a particular setting. In some real-world settings, such as randomized controlled trials or …
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
YongganFu, HaoranYou, YangZhao....
Published date-12/01/2020
Quantization
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due …