相关论文: Exploiting the Short-term to Long-term Plasticity …

Efficient representation learning is essential for optimal information storage and classification. However, it is frequently overlooked in artificial neural networks (ANNs). This neglect results in networks that can become overparameterized…

An extreme learning machine (ELM) can be regarded as a two stage feed-forward neural network (FNN) learning system which randomly assigns the connections with and within hidden neurons in the first stage and tunes the connections with…

Large language models (LLMs) have garnered substantial attention due to their promising applications in diverse domains. Nevertheless, the increasing size of LLMs comes with a significant surge in the computational requirements for training…

Construction and training principles have been proposed and tested for an artificial neural network based on metal-oxide thin-film nanostructures possessing bipolar resistive switching (memristive) effect. Experimental electronic circuit of…

Simulation frameworks such MemTorch, DNN+NeuroSim, and aihwkit are commonly used to facilitate the end-to-end co-design of memristive machine learning (ML) accelerators. These simulators can take device nonidealities into account and are…

On-chip learning in a crossbar array based analog hardware Neural Network (NN) has been shown to have major advantages in terms of speed and energy compared to training NN on a traditional computer. However analog hardware NN proposals and…

Achieving personalized intelligence at the edge with real-time learning capabilities holds enormous promise in enhancing our daily experiences and helping decision making, planning, and sensing. However, efficient and reliable edge learning…

We present here a new approach for using the intelligence aspects of artificial intelligence for knowledge discovery rather than device optimization in electromagnetic (EM) nanostructures. This approach uses training data obtained through…

The tracking method based on the extreme learning machine (ELM) is efficient and effective. ELM randomly generates input weights and biases in the hidden layer, and then calculates and computes the output weights by reducing the iterative…

Photonic neural networks offer a promising alternative to traditional electronic systems for machine learning accelerators due to their low latency and energy efficiency. However, the challenge of implementing the backpropagation algorithm…

On-device learning allows AI models to adapt to user data, thereby enhancing service quality on edge platforms. However, training AI on resource-limited devices poses significant challenges due to the demanding computing workload and the…

While most neuromorphic systems are based on nanoscale electronic devices, nature relies on ions for energy-efficient information processing. Therefore, finding memristive nanofluidic devices is a milestone toward realizing electrolytic…

Conventional intelligent systems based on deep neural network (DNN) models encounter challenges in achieving human-like continual learning due to catastrophic forgetting. Here, we propose a metaplasticity model inspired by human working…

Large-scale integration of emerging nanoscale non-volatile memory devices, e.g. resistive random-access memory (RRAM), can enable a new generation of neuromorphic computers that can solve a wide range of machine learning problems. Such…

Crossbar array architecture is an essential design element for densely connected Non-Volatile Memory(NVM) applications. To overcome intrinsic sneak current problem of crossbar arrays, each memory unit is serially attached to a selector unit…

In extreme learning machines (ELM) the hidden-layer coefficients are randomly set and fixed, while the output-layer coefficients of the neural network are computed by a least squares method. The randomly-assigned coefficients in ELM are…

This paper reports a comprehensive study on the impacts of temperature-change, process variation, flicker noise and device aging on the inference accuracy of pre-trained all-ferroelectric (FE) FinFET deep neural networks.…

The optical properties of metallic nanoparticles are dominated by localized surface plasmons (LSPs). Their properties only depend on the constituting material, the size and shape of the nano-object as well as its surrounding medium. In…

Continual Learning (CL) is an emerging machine learning paradigm that aims to learn from a continuous stream of tasks without forgetting knowledge learned from the previous tasks. To avoid performance decrease caused by forgetting, prior…

Memristor based neural networks have great potentials in on-chip neuromorphic computing systems due to the fast computation and low-energy consumption. However, the imprecise properties of existing memristor devices generally result in…