Related papers: Challenges and Opportunities in Implementing Negat…
Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences. To address this limitation, we express the…
Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modest hardware requirements. Memristor-based circuits are particularly promising for RC, as…
Deep learning (DL) is characterised by its dynamic nature, with new deep neural network (DNN) architectures and approaches emerging every few years, driving the field's advancement. At the same time, the ever-increasing use of mobile…
Passing current at given threshold voltages through a metal/insulator/metal sandwich structure device may change its resistive state. Such resistive switching is unique to nanoscale devices, but its underlying physical mechanism remains…
As state of the art neural networks (NNs) continue to grow in size, their resource-efficient implementation becomes ever more important. In this paper, we introduce a compression scheme that reduces the number of computations required for…
Recently, recurrent neural network transducer (RNN-T) gains increasing popularity due to its natural streaming capability as well as superior performance. Nevertheless, RNN-T training requires large time and computation resources as RNN-T…
Recurrent Neural Networks (RNNs) are an important class of neural networks designed to retain and incorporate context into current decisions. RNNs are particularly well suited for machine learning problems in which context is important,…
Memristors as emergent nano-electronic devices have been successfully fabricated and used in non-conventional and neuromorphic computing systems in the last years. Several behavioral or physical based models have been developed to explain…
Numerous proposed and developed superconducting fault current limiters and self-limiting transformers limit successfully fault currents but do not provide uninterrupted supplying of consumers. A design investigated in the work combines the…
Neural Radiance Fields (NeRF), an AI-driven approach for 3D view reconstruction, has demonstrated impressive performance, sparking active research across fields. As a result, a range of advanced NeRF models has emerged, leading on-device…
The performance limits of the multilayer graphene nanoribbon (GNR) field-effect transistor (FET) are assessed and compared to those of monolayer GNR FET and carbon nanotube (CNT) FET. The results show that with a thin high-k gate insulator…
Biometrics on mobile devices has attracted a lot of attention in recent years as it is considered a user-friendly authentication method. This interest has also been motivated by the success of Deep Learning (DL). Architectures based on…
Recent works use the Neural radiance field (NeRF) to perform multi-view 3D reconstruction, providing a significant leap in rendering photorealistic scenes. However, despite its efficacy, NeRF exhibits limited capability of learning…
Reservoir computing (RC) is attracting attention as a machine-learning technique for edge computing. In time-series classification tasks, the number of features obtained using a reservoir depends on the length of the input series.…
While it seems counterintuitive to think of degradation within an operating device as beneficial, one may argue that when rationally designed, the controlled breakdown of materials can be harnessed for specific functions. To apply this…
Present-day Deep Reinforcement Learning (RL) systems show great promise towards building intelligent agents surpassing human-level performance. However, the computational complexity associated with the underlying deep neural networks (DNNs)…
Semiconductor quantum dots are useful for controlling and observing quantum states and can also be used as sensors for reading out quantum bits and exploring local electronic states in nanostructures. However, challenges remain for the…
Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of…
Reconfigurable intelligent surfaces (RISs) are typically used in multi-user systems to mitigate interference among active transmitters. In contrast, this paper studies a setting with a conventional active encoder as well as a passive…
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the…