Abstract Bayesian networks (BNs) find widespread application in many real-world probabilistic problems including diagnostics, forecasting, computer vision, etc. The basic computing primitive for BNs is a stochastic bit (s-bit) generator that can control the probability of obtaining ‘1’ in a binary bit-stream. While silicon-based complementary metal-oxide-semiconductor (CMOS) technology can be used for hardware implementation of BNs, the lack of inherent stochasticity makes it area and energy inefficient. On the other hand, memristors and spintronic devices offer inherent stochasticity but lack computing ability beyond simple vector matrix multiplication due to their two-terminal nature and rely on extensive CMOS peripherals for BN implementation, which limits area and energy efficiency. Here, we circumvent these challenges by introducing a hardware platform based on 2D memtransistors. First, we experimentally demonstrate a low-power and compact s-bit generator circuit that exploits cycle-to-cycle fluctuation in the post-programmed conductance state of 2D memtransistors. Next, the s-bit generators are monolithically integrated with 2D memtransistor-based logic gates to implement BNs. Our findings highlight the potential for 2D memtransistor-based integrated circuits for non-von Neumann computing applications.
This content will become publicly available on December 1, 2023
Two-dimensional materials-based probabilistic synapses and reconfigurable neurons for measuring inference uncertainty using Bayesian neural networks
Abstract Artificial neural networks have demonstrated superiority over traditional computing architectures in tasks such as pattern classification and learning. However, they do not measure uncertainty in predictions, and hence they can make wrong predictions with high confidence, which can be detrimental for many mission-critical applications. In contrast, Bayesian neural networks (BNNs) naturally include such uncertainty in their model, as the weights are represented by probability distributions (e.g. Gaussian distribution). Here we introduce three-terminal memtransistors based on two-dimensional (2D) materials, which can emulate both probabilistic synapses as well as reconfigurable neurons. The cycle-to-cycle variation in the programming of the 2D memtransistor is exploited to achieve Gaussian random number generator-based synapses, whereas 2D memtransistor based integrated circuits are used to obtain neurons with hyperbolic tangent and sigmoid activation functions. Finally, memtransistor-based synapses and neurons are combined in a crossbar array architecture to realize a BNN accelerator for a data classification task.
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- Nature Communications
- Sponsoring Org:
- National Science Foundation
More Like this
Energy-Efficient Deep Neural Networks with Mixed-Signal Neurons and Dense-Local and Sparse-Global ConnectivityNeuromorphic Computing has become tremendously popular due to its ability to solve certain classes of learning tasks better than traditional von-Neumann computers. Data-intensive classification and pattern recognition problems have been of special interest to Neuromorphic Engineers, as these problems present complex use-cases for Deep Neural Networks (DNNs) which are motivated from the architecture of the human brain, and employ densely connected neurons and synapses organized in a hierarchical manner. However, as these systems become larger in order to handle an increasing amount of data and higher dimensionality of features, the designs often become connectivity constrained. To solve this, the computation is divided into multiple cores/islands, called processing engines (PEs). Today, the communication among these PEs are carried out through a power-hungry network-on-chip (NoC), and hence the optimal distribution of these islands along with energy-efficient compute and communication strategies become extremely important in reducing the overall energy of the neuromorphic computer, which is currently orders of magnitude higher than the biological human brain. In this paper, we extensively analyze the choice of the size of the islands based on mixed-signal neurons/synapses for 3-8 bit-resolution within allowable ranges for system-level classification error, determined by the analog non-idealities (noise and mismatch) in themore »
We develop a convex analytic framework for ReLU neural networks which elucidates the inner workings of hidden neurons and their function space characteristics. We show that neural networks with rectified linear units act as convex regularizers, where simple solutions are encouraged via extreme points of a certain convex set. For one dimensional regression and classification, as well as rank-one data matrices, we prove that finite two-layer ReLU networks with norm regularization yield linear spline interpolation. We characterize the classification decision regions in terms of a closed form kernel matrix and minimum L1 norm solutions. This is in contrast to Neural Tangent Kernel which is unable to explain neural network predictions with finitely many neurons. Our convex geometric description also provides intuitive explanations of hidden neurons as auto encoders. In higher dimensions, we show that the training problem for two-layer networks can be cast as a finite dimensional convex optimization problem with infinitely many constraints. We then provide a family of convex relaxations to approximate the solution, and a cutting-plane algorithm to improve the relaxations. We derive conditions for the exactness of the relaxations and provide simple closed form formulas for the optimal neural network weights in certain cases. We alsomore »
Rainey, Larry B. ; Holland, O. Thomas (Ed.)Biological neural networks offer some of the most striking and complex examples of emergence ever observed in natural or man-made systems. Individually, the behavior of a single neuron is rather simple, yet these basic building blocks are connected through synapses to form neural networks, which are capable of sophisticated capabilities such as pattern recognition and navigation. Lower-level functionality provided by a given network is combined with other networks to produce more sophisticated capabilities. These capabilities manifest emergently at two vastly different, yet interconnected time scales. At the time scale of neural dynamics, neural networks are responsible for turning noisy external stimuli and internal signals into signals capable of supporting complex computations. A key component in this process is the structure of the network, which itself forms emergently over much longer time scales based on the outputs of its constituent neurons, a process called learning. The analysis and interpretation of the behaviors of these interconnected dynamical systems of neurons should account for the network structure and the collective behavior of the network. The field of graph signal processing (GSP) combines signal processing with network science to study signals defined on irregular network structures. Here, we show that GSP can be amore »
Traditional deep neural networks (NNs) have significantly contributed to the state-of-the-art performance in the task of classification under various application domains. However, NNs have not considered inherent uncertainty in data associated with the class probabilities where misclassification under uncertainty may easily introduce high risk in decision making in real-world contexts (e.g., misclassification of objects in roads leads to serious accidents). Unlike Bayesian NN that indirectly infer uncertainty through weight uncertainties, evidential NNs (ENNs) have been recently proposed to explicitly model the uncertainty of class probabilities and use them for classification tasks. An ENN offers the formulation of the predictions of NNs as subjective opinions and learns the function by collecting an amount of evidence that can form the subjective opinions by a deterministic NN from data. However, the ENN is trained as a black box without explicitly considering inherent uncertainty in data with their different root causes, such as vacuity (i.e., uncertainty due to a lack of evidence) or dissonance (i.e., uncertainty due to conflicting evidence). By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem. We took a hybrid approach that combines Wasserstein Generative Adversarial Network (WGAN)more »