Related papers: Improving the Performance and Learning Stability o…
The use of Recurrent Neural Networks (RNNs) for system identification has recently gathered increasing attention, thanks to their black-box modeling capabilities.Albeit RNNs have been fruitfully adopted in many applications, only few works…
We propose a novel memory-enhancing mechanism for recurrent neural networks that exploits the effect of human cognitive appraisal in sequential assessment tasks. We conceptualize the memory-enhancing mechanism as Reinforcement Memory Unit…
Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this…
Gated recurrent units (GRUs) are specialized memory elements for building recurrent neural networks. Despite their incredible success on various tasks, including extracting dynamics underlying neural data, little is understood about the…
Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive…
Accurate prediction of the remaining useful life (RUL) of industrial machinery is essential for reducing downtime and optimizing maintenance schedules. Existing approaches, such as long short-term memory (LSTM) networks and convolutional…
Catastrophic forgetting and capacity saturation are the central challenges of any parametric lifelong learning system. In this work, we study these challenges in the context of sequential supervised learning with an emphasis on recurrent…
Binary neural networks (BNNs) have received increasing attention due to their superior reductions of computation and memory. Most existing works focus on either lessening the quantization error by minimizing the gap between the…
Residual units are wildly used for alleviating optimization difficulties when building deep neural networks. However, the performance gain does not well compensate the model size increase, indicating low parameter efficiency in these…
Cardiovascular disease (CVD) remains the leading cause of mortality worldwide, underscoring the need for reliable and efficient predictive tools that support early intervention. Traditional diagnostic approaches rely on handcrafted features…
The light gated recurrent units (Li-GRU) is well-known for achieving impressive results in automatic speech recognition (ASR) tasks while being lighter and faster to train than a standard gated recurrent units (GRU). However, the unbounded…
As the size of artificial intelligence and machine learning (AI/ML) models and datasets grows, the memory bandwidth becomes a critical bottleneck. The paper presents a novel extended memory hierarchy that addresses some major memory…
Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…
Designing deep neural networks is an art that often involves an expensive search over candidate architectures. To overcome this for recurrent neural nets (RNNs), we establish a connection between the hidden state dynamics in an RNN and…
State-of-the-art sequential recommendation relies heavily on self-attention-based recommender models. Yet such models are computationally expensive and often too slow for real-time recommendation. Furthermore, the self-attention operation…
Recurrent Neural Networks (RNNs) are a key technology for emerging applications such as automatic speech recognition, machine translation or image description. Long Short Term Memory (LSTM) networks are the most successful RNN…
Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input…
We investigate recurrent neural network architectures for event-sequence processing. Event sequences, characterized by discrete observations stamped with continuous-valued times of occurrence, are challenging due to the potentially wide…
Advancements in parallel processing have lead to a surge in multilayer perceptrons' (MLP) applications and deep learning in the past decades. Recurrent Neural Networks (RNNs) give additional representational power to feedforward MLPs by…