Related papers: Hardware-aware $in \ situ$ Boltzmann machine learn…
Macroscopic spin ensembles possess brain-like features such as non-linearity, plasticity, stochasticity, selfoscillations, and memory effects, and therefore offer opportunities for neuromorphic computing by spintronics devices. Here we…
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…
Air hockey demands split-second decisions at high puck velocities, a challenge we address with a compact network of spiking neurons running on a mixed-signal analog/digital neuromorphic processor. By co-designing hardware and learning…
Spin-based computing is emerging as a powerful approach for energy-efficient and high-performance solutions to future data processing hardware. Spintronic devices function by electrically manipulating the collective dynamics of the electron…
Stochastic diffusion processes are pervasive in nature, from the seemingly erratic Brownian motion to the complex interactions of synaptically-coupled spiking neurons. Recently, drawing inspiration from Langevin dynamics, neuromorphic…
The Bayesian view of the brain hypothesizes that the brain constructs a generative model of the world, and uses it to make inferences via Bayes' rule. Although many types of approximate inference schemes have been proposed for hierarchical…
Bayesian networks play an increasingly important role in data mining, inference, and reasoning with the rapid development of artificial intelligence. In this paper, we present proof-of-concept experiments demonstrating the use of spin-orbit…
Voltage-driven spin transfer torques in magnetic tunnel junctions provide an outstanding tool to design advanced spin-based devices for memory and reprogrammable logic applications. The non-linear voltage dependence of the torque has a…
Probabilistic machine learning enabled by the Bayesian formulation has recently gained significant attention in the domain of automated reasoning and decision-making. While impressive strides have been made recently to scale up the…
Binarized Neural Networks, a recently discovered class of neural networks with minimal memory requirements and no reliance on multiplication, are a fantastic opportunity for the realization of compact and energy efficient inference…
Recently, in the paper "Weight Agnostic Neural Networks" Gaier & Ha utilized architecture search to find networks where the topology completely encodes the knowledge. However, architecture search in topology space is expensive. We use the…
Understanding how the brain learns to compute functions reliably, efficiently and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could…
Neuromorphic computing, commonly understood as a computing approach built upon neurons, synapses, and their dynamics, as opposed to Boolean gates, is gaining large mindshare due to its direct application in solving current and future…
Memristive neural networks (MNNs), which use memristors as neurons or synapses, have become a hot research topic recently. However, most memristors are not compatible with mainstream integrated circuit technology and their stabilities in…
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…
Stochastic p-Bit devices play a pivotal role in solving NP-hard problems, neural network computing, and hardware accelerators for algorithms such as the simulated annealing. In this work, we focus on Stochastic p-Bits based on high-barrier…
Magnetic tunnel junctions operating in the superparamagnetic regime are promising devices in the field of probabilistic computing, which is suitable for applications like high-dimensional optimization or sampling problems. Further, random…
This work proposes an end-to-end multi-modal reinforcement learning framework for high-level decision-making in autonomous vehicles. The framework integrates heterogeneous sensory input, including camera images, LiDAR point clouds, and…
Spiking recurrent neural networks (RNNs) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing. However training spiking RNNs on dedicated…
We present results from a new approach to learning and plasticity in neuromorphic hardware systems: to enable flexibility in implementable learning mechanisms while keeping high efficiency associated with neuromorphic implementations, we…