Related papers: Plasticity-Enhanced Domain-Wall MTJ Neural Network…

It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability…

The millimeter wave (mmWave) multiuser multiple-input multiple-output (MU-MIMO) systems with discrete lens arrays (DLA) have received great attention due to their simple hardware implementation and excellent performance. In this work, we…

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its…

Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and…

Quantized neural networks (QNNs) are being actively researched as a solution for the computational complexity and memory intensity of deep neural networks. This has sparked efforts to develop algorithms that support both inference and…

Deep neural network (DNN) models have become increasingly crucial components in intelligent software systems. However, training a DNN model is typically expensive in terms of both time and money. To address this issue, researchers have…

Deep neural networks have achieved impressive performance through carefully engineered training strategies. Nonetheless, such methods lack parallels in biological neural circuits, relying heavily on non-local credit assignment, precise…

A growing body of evidence suggests that neural networks employed in deep reinforcement learning (RL) gradually lose their plasticity, the ability to learn from new data; however, the analysis and mitigation of this phenomenon is hampered…

Serial connection of multiple memory cells using perpendicular magnetic tunnel junctions (pMTJ) is proposed as a way to increase magnetic random access memory (MRAM) storage density. Multi-bit storage element is designed using pMTJs…

The straintronic magnetic tunnel junction (s-MTJ) is an MTJ whose resistance state can be changed continuously or gradually from high to low with a gate voltage that generates strain the magnetostrictive soft layer. This unusual feature,…

In this paper, we present a new MTL framework that searches for structures optimized for multiple tasks with diverse graph topologies and shares features among tasks. We design a restricted DAG-based central network with read-in/read-out…

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other…

We investigate recurrent neural networks with asymmetric interactions and demonstrate that the inclusion of self-couplings or sparse excitatory inter-module connections leads to the emergence of a densely connected manifold of dynamically…

Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are…

Control of magnetism without using magnetic fields enables large-scale integration of spintronic devices for memory, computation and communication in the beyond-CMOS era. Mechanisms including spin torque transfer, spin Hall effect, and…

We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We…

Spintronic artificial spiking neurons are promising due to their ability to closely mimic the leaky integrate-and-fire (LIF) dynamics of the biological LIF spiking neuron. However, the neuron needs to be reset after firing. Few of the…

Flexible electronics is an emerging field in many applications ranging from in vivo biomedical devices to wearable smart systems. The capability of conforming to curved surfaces opens the door to add electronic components to miniaturized…

In this study, a machine learning-based technique is developed to reduce the computational cost required to explore large design spaces of substitutional alloys. The first advancement is based on a neural network approach to predict the…

Conventional computing paradigm struggles to fulfill the rapidly growing demands from emerging applications, especially those for machine intelligence, because much of the power and energy is consumed by constant data transfers between…