Related papers: On-device Synaptic Memory Consolidation using Fowl…

A Boltzmann machine whose effective "temperature" can be dynamically "cooled" provides a stochastic neural network realization of simulated annealing, which is an important metaheuristic for solving combinatorial or global optimization…

Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) are useful for many practical tasks in machine learning. Synaptic weights, as well as neuron activation functions within the deep network are typically stored with…

To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning a new task, the proposed method preserves the knowledge for…

Synaptic memory is considered to be the main element responsible for learning and cognition in humans. Although traditionally non-volatile long-term plasticity changes have been implemented in nanoelectronic synapses for neuromorphic…

Block-sequential continual learning demands that a single model both protect prior solutions from catastrophic forgetting and efficiently infer at inference time which prior solution matches the current input without task labels. We present…

Deep neural networks (DNNs) have revolutionized the field of artificial intelligence and have achieved unprecedented success in cognitive tasks such as image and speech recognition. Training of large DNNs, however, is computationally…

Ferroelectric tunnel junctions (FTJ) based on hafnium zirconium oxide (Hf1-xZrxO2; HZO) are a promising candidate for future applications, such as low-power memories and neuromorphic computing. The tunneling electroresistance (TER) is…

Quantum annealers can provide non-local optimization by tunneling between states in a process that ideally eliminates memory of the initial configuration. We study the crossover between memory loss and retention due to quantum fluctuations,…

Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures. However, due to the non-differentiable nature of spiking neuronal functions, the standard error…

Spiking neural networks (SNNs), as one of the brain-inspired models, has spatio-temporal information processing capability, low power feature, and high biological plausibility. The effective spatio-temporal feature makes it suitable for…

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Synergistic…

Federated Learning (FL) is a promising distributed machine learning framework that allows collaborative learning of a global model across decentralized devices without uploading their local data. However, in real-world FL scenarios, the…

Spiking Neural Networks (SNNs) are widely deployed to solve complex pattern recognition, function approximation and image classification tasks. With the growing size and complexity of these networks, hardware implementation becomes…

Recurrent Neural Networks (RNNs) have the ability to retain memory and learn data sequences. Due to the recurrent nature of RNNs, it is sometimes hard to parallelize all its computations on conventional hardware. CPUs do not currently offer…

Quantum memory, a pivotal hub in quantum information processing, is expected to achieve high-performance storage and coherent manipulation of quantum states, with memory efficiency exceeding 90% and quantum fidelity surpassing the…

Convolutional Neural Networks (CNNs) are used to evaluate accelerometer and microphone data for bearing and induction motor diagnosis. A Long Short-Term Memory (LSTM) recurrent neural network is used to combine sensor information…

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to…

Emerging AI accelerators have started to gain attention and offer new opportunities for efficient inference of large language models (LLMs). Trainium, an AI accelerator recently developed by Amazon Web Services (AWS), provides an attractive…

The T centre, a silicon-native spin-photon interface with telecommunications-band optical transitions and long-lived microwave qubits, offers an appealing new platform for both optical quantum memory and microwave to optical…

We propose Wake-Sleep Consolidated Learning (WSCL), a learning strategy leveraging Complementary Learning System theory and the wake-sleep phases of the human brain to improve the performance of deep neural networks for visual…