Search Results for author:
Found 5 papers, 2 papers with code
Foundations of a temporal RL
Spiking across populations of neurons in many regions of the mammalian brain maintains a robust temporal memory, a neural timeline of the recent past.
A deep convolutional neural network that is invariant to time rescaling
This property, inspired by findings from contemporary neuroscience and consistent with findings from cognitive psychology, may enable networks that learn with fewer training examples, fewer weights and that generalize more robustly to out of sample data.
DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales
SITH modules respond to their inputs with a geometrically-spaced set of time constants, enabling the DeepSITH network to learn problems along a continuum of time-scales.
Estimating scale-invariant future in continuous time
Widely used reinforcement learning algorithms discretize continuous time and estimate either transition functions from one step to the next (model-based algorithms) or a scalar value of exponentially-discounted future reward using the Bellman equation (model-free algorithms).
Scale-invariant temporal history (SITH): optimal slicing of the past in an uncertain world
In both the human brain and any general artificial intelligence (AI), a representation of the past is necessary to predict the future.
