Related papers: Sparse Attentive Backtracking: Temporal CreditAssi…

In many daily tasks we make multiple decisions before reaching a goal. In order to learn such sequences of decisions, a mechanism to link earlier actions to later reward is necessary. Reinforcement learning theory suggests two classes of…

While Truncated Back-Propagation through Time (BPTT) is the most popular approach to training Recurrent Neural Networks (RNNs), it suffers from being inherently sequential (making parallelization difficult) and from truncating gradient flow…

Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data. We introduce the concept of modifying the cell state (memory) of LSTMs using…

How physical networks of neurons, bound by spatio-temporal locality constraints, can perform efficient credit assignment, remains, to a large extent, an open question. In machine learning, the answer is almost universally given by the error…

Recurrent Neural Networks (RNNs) are useful in temporal sequence tasks. However, training RNNs involves dense matrix multiplications which require hardware that can support a large number of arithmetic operations and memory accesses.…

Spiking neural networks (SNN) are usually more energy-efficient as compared to Artificial neural networks (ANN), and the way they work has a great similarity with our brain. Back-propagation (BP) has shown its strong power in training ANN…

The need to recognise long-term dependencies in sequential data such as video streams has made Long Short-Term Memory (LSTM) networks a prominent Artificial Intelligence model for many emerging applications. However, the high computational…

Transfer learning aims to solve the data sparsity for a target domain by applying information of the source domain. Given a sequence (e.g. a natural language sentence), the transfer learning, usually enabled by recurrent neural network…

Attention-based autoregressive models have achieved state-of-the-art performance in various sequence-to-sequence tasks, including Text-To-Speech (TTS) and Neural Machine Translation (NMT), but can be difficult to train. The standard…

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on temporal-difference algorithms for selective credit assignment. These selective algorithms…

Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production,…

Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of…

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

We introduce a new method for internal replay that modulates the frequency of rehearsal based on the depth of the network. While replay strategies mitigate the effects of catastrophic forgetting in neural networks, recent works on…

Backpropagation (BP) has been pivotal in advancing machine learning and remains essential in computational applications and comparative studies of biological and artificial neural networks. Despite its widespread use, the implementation of…

The question of how to determine which states and actions are responsible for a certain outcome is known as the credit assignment problem and remains a central research question in reinforcement learning and artificial intelligence.…

Existing machines are functionally specific tools that were made for easy prediction and control. Tomorrow's machines may be closer to biological systems in their mutability, resilience, and autonomy. But first they must be capable of…

The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient. While spiking neural networks (SNNs) allow for efficient…

Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are…

Recurrent Neural Networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, Long-Short-Term-Memory Networks (LSTMs) are commonly preferred in practice, as these…