Related papers: A ballistic transport model for an artificial neur…

The field of artificial intelligence faces significant challenges in achieving both biological plausibility and computational efficiency, particularly in visual learning tasks. Current artificial neural networks, such as convolutional…

The brain can efficiently learn a wide range of tasks, motivating the search for biologically inspired learning rules for improving current artificial intelligence technology. Most biological models are composed of point neurons, and cannot…

In daily life situations, we have to perform multiple tasks given a visual stimulus, which requires task-relevant information to be transmitted through our visual system. When it is not possible to transmit all the possibly relevant…

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…

Recent years have witnessed growing interest in the use of Artificial Neural Networks (ANNs) for vision, classification, and inference problems. An artificial neuron sums N weighted inputs and passes the result through a non-linear transfer…

The continuous effort in making artificial neural networks more alike to human brain calls for the hardware elements to implement biological synapse-like functionalities. The recent experimental demonstration of ferroelectric-like FETs…

The effectiveness and performance of artificial neural networks, particularly for visual tasks, depends in crucial ways on the receptive field of neurons. The receptive field itself depends on the interplay between several architectural…

We describe the operation of a neuronal device which embodies the computational principles of the `paper-and-pencil' machine envisioned by Alan Turing. The network is based on principles of cortical organization. We develop a plausible…

Previous work has shown that it is possible to train deep neural networks with low precision weights and activations. In the extreme case it is even possible to constrain the network to binary values. The costly floating point…

As it is getting increasingly difficult to achieve gains in the density and power efficiency of microelectronic computing devices because of lithographic techniques reaching fundamental physical limits, new approaches are required to…

In this paper, a simple, general method of adding auxiliary stochastic neurons to a multi-layer perceptron is proposed. It is shown that the proposed method is a generalization of recently successful methods of dropout (Hinton et al.,…

We investigate the efficient transmission and processing of weak, subthreshold signals in a realistic neural medium in the presence of different levels of the underlying noise. Assuming Hebbian weights for maximal synaptic conductances --…

Artificial neural networks have diverged far from their early inspiration in neurology. In spite of their technological and commercial success, they have several shortcomings, most notably the need for a large number of training examples…

Transport through semiconductor nanostructures is a quantum-coherent process. This paper focuses on systems in which the electron's dynamics is ballistic and the transport is dominated by the scattering from structure boundaries. Opposite…

In artificial neural networks trained with gradient descent, the weights used for processing stimuli are also used during backward passes to calculate gradients. For the real brain to approximate gradients, gradient information would have…

Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for developing and deploying neural networks whose weight…

Many recent generative models make use of neural networks to transform the probability distribution of a simple low-dimensional noise process into the complex distribution of the data. This raises the question of whether biological networks…

We introduce a novel neuromorphic network architecture based on a lattice of exciton-polariton condensates, intricately interconnected and energized through non-resonant optical pumping. The network employs a binary framework, where each…

Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally efficient, this design implicitly behaves like a mean-based estimator and is…

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…