Surprising events trigger measurable brain activity and influence human
...
We consider the problem of training a neural network to store a set of
p...
Abstract object properties and their relations are deeply rooted in huma...
Fitting network models to neural activity is becoming an important tool ...
We study how permutation symmetries in overparameterized multi-layer neu...
Surprise-based learning allows agents to adapt quickly in non-stationary...
The permutation symmetry of neurons in each layer of a deep neural netwo...
Training deep neural networks with the error backpropagation algorithm i...
Gaussian processes are a class of flexible nonparametric Bayesian tools ...
As deep learning advances, algorithms of music composition increase in
p...
Modern reinforcement learning algorithms reach super-human performance i...
Episodic control has been proposed as a third approach to reinforcement
...
In machine learning, error back-propagation in multi-layer neural networ...
A big challenge in algorithmic composition is to devise a model that is ...