Nadezhda Semenova

Nadezhda Semenova, Daniel Brunner

Physical neural networks are promising candidates for next generation artificial intelligence hardware. In such architectures, neurons and connections are physically realized and do not leverage digital concepts with their practically infinite signal-to-noise ratio to encode, transduce and transform information. They therefore are prone to noise with a variety of statistical and architectural properties, and effective strategies leveraging network-inherent assets to mitigate noise in an hardware-efficient manner are important in the pursuit of next generation neural network hardware. Based on analytical derivations, we here introduce and analyse a variety of different noise-mitigation approaches. We analytically show that intra-layer connections in which the connection matrix's squared mean exceeds the mean of its square fully suppresses uncorrelated noise. We go beyond and develop two synergistic strategies for noise that is uncorrelated and correlated across populations of neurons. First, we introduce the concept of ghost neurons, where each group of neurons perturbed by correlated noise has a negative connection to a single neuron, yet without receiving any input information. Secondly, we show that pooling of neuron populations is an efficient approach to suppress uncorrelated noise. As such, we developed a general noise mitigation strategy leveraging the statistical properties of the different noise terms most relevant in analogue hardware. Finally, we demonstrate the effectiveness of this combined approach for trained neural network classifying the MNIST handwritten digits, for which we achieve a 4-fold improvement of the output signal-to-noise ratio and increase the classification accuracy almost to the level of the noise-free network.

Nadezhda Semenova, Daniel Brunner

In recent years, the hardware implementation of neural networks, leveraging physical coupling and analog neurons has substantially increased in relevance. Such nonlinear and complex physical networks provide significant advantages in speed and energy efficiency, but are potentially susceptible to internal noise when compared to digital emulations of such networks. In this work, we consider how additive and multiplicative Gaussian white noise on the neuronal level can affect the accuracy of the network when applied for specific tasks and including a softmax function in the readout layer. We adapt several noise reduction techniques to the essential setting of classification tasks, which represent a large fraction of neural network computing. We find that these adjusted concepts are highly effective in mitigating the detrimental impact of noise.

Nadezhda Semenova

In recent years, more and more works have appeared devoted to the analog (hardware) implementation of artificial neural networks, in which neurons and the connection between them are based not on computer calculations, but on physical principles. Such networks offer improved energy efficiency and, in some cases, scalability, but may be susceptible to internal noise. This paper studies the influence of noise on the functioning of recurrent networks using the example of trained echo state networks (ESNs). The most common reservoir connection matrices were chosen as various topologies of ESNs: random uniform and band matrices with different connectivity. White Gaussian noise was chosen as the influence, and according to the way of its introducing it was additive or multiplicative, as well as correlated or uncorrelated. In the paper, we show that the propagation of noise in reservoir is mainly controlled by the statistical properties of the output connection matrix, namely the mean and the mean square. Depending on these values, more correlated or uncorrelated noise accumulates in the network. We also show that there are conditions under which even noise with an intensity of $10^{-20}$ is already enough to completely lose the useful signal. In the article we show which types of noise are most critical for networks with different activation functions (hyperbolic tangent, sigmoid and linear) and if the network is self-closed.

Nadezhda Semenova, Laurent Larger, Daniel Brunner

Deep neural networks unlocked a vast range of new applications by solving tasks of which many were previously deemed as reserved to higher human intelligence. One of the developments enabling this success was a boost in computing power provided by special purpose hardware, such as graphic or tensor processing units. However, these do not leverage fundamental features of neural networks like parallelism and analog state variables. Instead, they emulate neural networks relying on binary computing, which results in unsustainable energy consumption and comparatively low speed. Fully parallel and analogue hardware promises to overcome these challenges, yet the impact of analogue neuron noise and its propagation, i.e. accumulation, threatens rendering such approaches inept. Here, we determine for the first time the propagation of noise in deep neural networks comprising noisy nonlinear neurons in trained fully connected layers. We study additive and multiplicative as well as correlated and uncorrelated noise, and develop analytical methods that predict the noise level in any layer of symmetric deep neural networks or deep neural networks trained with back propagation. We find that noise accumulation is generally bound, and adding additional network layers does not worsen the signal to noise ratio beyond a limit. Most importantly, noise accumulation can be suppressed entirely when neuron activation functions have a slope smaller than unity. We therefore developed the framework for noise in fully connected deep neural networks implemented in analog systems, and identify criteria allowing engineers to design noise-resilient novel neural network hardware.

Nadezhda Semenova, Xavier Porte, Louis Andreoli et al.

We study and analyze the fundamental aspects of noise propagation in recurrent as well as deep, multi-layer networks. The main focus of our study are neural networks in analogue hardware, yet the methodology provides insight for networks in general. The system under study consists of noisy linear nodes, and we investigate the signal-to-noise ratio at the network's outputs which is the upper limit to such a system's computing accuracy. We consider additive and multiplicative noise which can be purely local as well as correlated across populations of neurons. This covers the chief internal-perturbations of hardware networks and noise amplitudes were obtained from a physically implemented recurrent neural network and therefore correspond to a real-world system. Analytic solutions agree exceptionally well with numerical data, enabling clear identification of the most critical components and aspects for noise management. Focusing on linear nodes isolates the impact of network connections and allows us to derive strategies for mitigating noise. Our work is the starting point in addressing this aspect of analogue neural networks, and our results identify notoriously sensitive points while simultaneously highlighting the robustness of such computational systems.