Unrolled computation graphs arise in many scenarios, including training RNNs, tuning
hyperparameters through unrolled optimization, and training learned optimizers. Current …

Online learning holds the promise of enabling efficient long-term credit assignment in
recurrent neural networks. However, current algorithms fall short of offline backpropagation …

We present a framework for compactly summarizing many recent results in efficient and/or
biologically plausible online training of recurrent neural networks (RNN). The framework …

Biological neural networks are equipped with an inherent capability to continuously adapt
through online learning. This aspect remains in stark contrast to learning with error …

How should state be constructed from a sequence of observations, so as to best achieve
some objective? Most deep learning methods update the parameters of the state …

Second-order optimizers are thought to hold the potential to speed up neural network
training, but due to the enormous size of the curvature matrix, they typically require …

Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks
(RNNs) offers certain conceptual advantages over backpropagation through time (BPTT) …

Current methods for training recurrent neural networks are based on backpropagation
through time, which requires storing a complete history of network states, and prohibits …

We propose a framework for online meta-optimization of parameters that govern
optimization, called Amortized Proximal Optimization (APO). We first interpret various …

State construction is important for learning in partially observable environments. A general
purpose strategy for state construction is to learn the state update using a Recurrent Neural …