This paper concerns itself with the task of taking a large trained neural network and 'compressing' it to be smaller by deleting parameters or entire neurons, with minimal decreases in the resulting model accuracy. We compare various methods of parameter and neuron selection: dropout-based neuron damage estimation, neuron merging, absolute-value based selection, random selection, OBD (Optimal Brain Damage). We also compare a variation on the classic OBD method that slightly o...

We look at the internal structure of neural networks which is usually treated as a black box. The easiest and the most comprehensible thing to do is to look at a binary classification and try to understand the approach a neural network takes. We review the significance of different activation functions, types of network architectures associated to them, and some empirical data. We find some interesting observations and a possibility to build upon the ideas to verify the proce...

Training neural networks means solving a high-dimensional optimization problem. Normally the goal is to minimize a loss function that depends on what is called the network function, or in other words the function that gives the network output given a certain input. This function depends on a large number of parameters, also known as weights, that depends on the network architecture. In general the goal of this optimization problem is to find the global minimum of the network ...

Neural networks have revolutionized many aspects of society but in the era of huge models with billions of parameters, optimizing and deploying them for commercial applications can require significant computational and financial resources. To address these challenges, we introduce the Tetra-AML toolbox, which automates neural architecture search and hyperparameter optimization via a custom-developed black-box Tensor train Optimization algorithm, TetraOpt. The toolbox also pro...

We present Differentiable Neural Architectures (DNArch), a method that jointly learns the weights and the architecture of Convolutional Neural Networks (CNNs) by backpropagation. In particular, DNArch allows learning (i) the size of convolutional kernels at each layer, (ii) the number of channels at each layer, (iii) the position and values of downsampling layers, and (iv) the depth of the network. To this end, DNArch views neural architectures as continuous multidimensional ...

Over the last few years, neural networks have started penetrating safety critical systems to take decisions in robots, rockets, autonomous driving car, etc. A problem is that these critical systems often have limited computing resources. Often, they use the fixed-point arithmetic for its many advantages (rapidity, compatibility with small memory devices.) In this article, a new technique is introduced to tune the formats (precision) of already trained neural networks using fi...

Map Space Exploration is the problem of finding optimized mappings of a Deep Neural Network (DNN) model on an accelerator. It is known to be extremely computationally expensive, and there has been active research looking at both heuristics and learning-based methods to make the problem computationally tractable. However, while there are dozens of mappers out there (all empirically claiming to find better mappings than others), the research community lacks systematic insights ...

Deploying machine learning-based intrusion detection systems (IDSs) on hardware devices is challenging due to their limited computational resources, power consumption, and network connectivity. Hence, there is a significant need for robust, deep learning models specifically designed with such constraints in mind. In this paper, we present a design methodology that automatically trains and evolves quantized neural network (NN) models that are a thousand times smaller than stat...

Our comprehension of biological neuronal networks has profoundly influenced the evolution of artificial neural networks (ANNs). However, the neurons employed in ANNs exhibit remarkable deviations from their biological analogs, mainly due to the absence of complex dendritic trees encompassing local nonlinearity. Despite such disparities, previous investigations have demonstrated that point neurons can functionally substitute dendritic neurons in executing computational tasks. ...

In this paper, we propose an algorithmic framework to automatically generate efficient deep neural networks and optimize their associated hyperparameters. The framework is based on evolving directed acyclic graphs (DAGs), defining a more flexible search space than the existing ones in the literature. It allows mixtures of different classical operations: convolutions, recurrences and dense layers, but also more newfangled operations such as self-attention. Based on this search...