Related papers: Machine learning using magnetic stochastic synapse…

The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neuroscience (aka. engrams)…

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is…

Reducing energy consumption has become a pressing need for modern machine learning, which has achieved many of its most impressive results by scaling to larger and more energy-consumptive neural networks. Unfortunately, the main algorithm…

This paper highlights new opportunities for designing large-scale machine learning systems as a consequence of blurring traditional boundaries that have allowed algorithm designers and application-level practitioners to stay -- for the most…

Neural networks with binary weights are computation-efficient and hardware-friendly, but their training is challenging because it involves a discrete optimization problem. Surprisingly, ignoring the discrete nature of the problem and using…

In neuromorphic computing, artificial synapses provide a multi-weight conductance state that is set based on inputs from neurons, analogous to the brain. Additional properties of the synapse beyond multiple weights can be needed, and can…

We demonstrate that extremely low resolution quantized (nominally 5-state) synapses with large stochastic variations in Domain Wall (DW) position can be both energy efficient and achieve reasonably high testing accuracies compared to Deep…

Stochastic neurons are extremely efficient hardware for solving a large class of problems and usually come in two varieties -- "binary" where the neuronal statevaries randomly between two values of -1, +1 and "analog" where the neuronal…

Spiking Neural Networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking…

Most normative models in computational neuroscience describe the task of learning as the optimisation of a cost function with respect to a set of parameters. However, learning as optimisation fails to account for a time varying environment…

Artificial Neural Networks (ANNs) are currently being used as function approximators in many state-of-the-art Reinforcement Learning (RL) algorithms. Spiking Neural Networks (SNNs) have been shown to drastically reduce the energy…

Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically…

Binary Spiking Neural Networks (BSNNs) inherit the eventdriven paradigm of SNNs, while also adopting the reduced storage burden of binarization techniques. These distinct advantages grant BSNNs lightweight and energy-efficient…

Spiking neural networks are nature's versatile solution to fault-tolerant and energy efficient signal processing. To translate these benefits into hardware, a growing number of neuromorphic spiking neural network processors attempt to…

Many real-world mission-critical applications require continual online learning from noisy data and real-time decision making with a defined confidence level. Probabilistic models and stochastic neural networks can explicitly handle…

Neural networks (NN)-based learning algorithms are strongly affected by the choices of initialization and data distribution. Different optimization strategies have been proposed for improving the learning trajectory and finding a better…

Neuromorphic networks of artificial neurons and synapses can solve computational hard problems with energy efficiencies unattainable for von Neumann architectures. For image processing, silicon neuromorphic processors outperform graphic…

Wave-guide-based physical systems provide a promising route toward energy-efficient analog computing beyond traditional electronics. Within this landscape, acoustic neural networks represent a promising approach for achieving low-power…

The brain is not only constrained by energy needed to fuel computation, but it is also constrained by energy needed to form memories. Experiments have shown that learning simple conditioning tasks already carries a significant metabolic…

Deep Neural Networks (DNN) have achieved human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power. Brain-inspired spiking neuromorphic chips consume low…