Related papers: Composable Probabilistic Inference Networks Using …

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

This paper presents a memristor-based compute-in-memory hardware accelerator for on-chip training and inference, focusing on its accuracy and efficiency against device variations, conductance errors, and input noise. Utilizing realistic…

In recent years, scientific machine learning, particularly physic-informed neural networks (PINNs), has introduced new innovative methods to understanding the differential equations that describe power system dynamics, providing a more…

Probabilistic spin logic (PSL), based on networks of binary stochastic neurons (or p-bits), has been shown to provide a viable framework for many functionalities including Ising computing, Bayesian inference, invertible Boolean logic and…

The computational demands of deep learning motivate the investigation of alternative approaches to computation. One alternative is physical neural networks~(PNNs), in which learning and inference are performed directly via physical…

Applications of Binary Neural Networks (BNNs) are promising for embedded systems with hard constraints on computing power. Contrary to conventional neural networks with the floating-point datatype, BNNs use binarized weights and activations…

The performance and efficiency of running large-scale datasets on traditional computing systems exhibit critical bottlenecks due to the existing "power wall" and "memory wall" problems. To resolve those problems, processing-in-memory (PIM)…

Inferring biophysical parameters and hidden state variables from partial and noisy observations is a fundamental challenge in computational neuroscience. This problem is particularly difficult for fast - slow spiking and bursting models,…

Energy efficient sampling with probabilistic neurons or p-bits has been demonstrated in the context of Boltzmann machines and it is natural to ask if these approaches can be extended to the field of generative AI where energy costs have…

Verification of binary neural network (BNN) robustness is NP-hard, as it can be formulated as a combinatorial search for an adversarial perturbation that induces misclassification. Exact verification methods therefore scale poorly with…

The need for deep neural network (DNN) models with higher performance and better functionality leads to the proliferation of very large models. Model training, however, requires intensive computation time and energy. Memristor-based…

Combining machine learning with physics is a trending approach for discovering unknown dynamics, and one of the most intensively studied frameworks is the physics-informed neural network (PINN). However, PINN often fails to optimize the…

While deep neural networks (DNNs) are used for prediction, inference on DNN-estimated subject-specific means for categorical or exponential family outcomes remains underexplored. We address this by proposing a DNN estimator under…

Neuromorphic Multiply-And-Accumulate (MAC) circuits utilizing synaptic weight elements based on SRAM or novel Non-Volatile Memories (NVMs) provide a promising approach for highly efficient hardware representations of neural networks. NVM…

This paper presents a PVT-resilient, subthreshold SRAM-based computing-in-memory (CIM) macro tailored for energy-efficient spiking neural networks (SNNs). The macro integrates in-situ current sensors and distributed voltage regulators to…

The possibility of using non-deterministic circuit components has been gaining significant attention in recent years. The modeling and simulation of their circuits require novel approaches, as now the state of a circuit at an arbitrary…

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Deep Boltzmann Machines (DBMs) are generative neural networks with these desired properties. We integrate a DBM…

Resistive Random Access Memory (ReRAM) based Processing In Memory (PIM) Accelerator has emerged as a promising computing architecture for memory intensive applications, such as Deep Neural Networks (DNNs). However, due to its immaturity,…

Binary stochastic neurons (BSN's) form an integral part of many machine learning algorithms, motivating the development of hardware accelerators for this complex function. It has been recognized that hardware BSN's can be implemented using…

Machine learning for scientific applications faces the challenge of limited data. We propose a framework that leverages a priori known physics to reduce overfitting when training on relatively small datasets. A deep neural network is…