Related papers: Tensorized NeuroEvolution of Augmenting Topologies…

NSGA-III is one of the most widely adopted algorithms for tackling many-objective optimization problems. However, its CPU-based design severely limits scalability and computational efficiency. To address the limitations, we propose…

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this…

We introduce the CUDA Tensor Transpose (cuTT) library that implements high-performance tensor transposes for NVIDIA GPUs with Kepler and above architectures. cuTT achieves high performance by (a) utilizing two GPU-optimized transpose…

Neuroevolution is one of the methodologies that can be used for learning optimal architecture during training. It uses evolutionary algorithms to generate the topology of artificial neural networks and its parameters. The main benefits are…

This paper presents a new Statistical Forward Planning (SFP) method, Rolling Horizon NeuroEvolution of Augmenting Topologies (rhNEAT). Unlike traditional Rolling Horizon Evolution, where an evolutionary algorithm is in charge of evolving a…

Convolutional neural networks show outstanding results in a variety of computer vision tasks. However, a neural network architecture design usually faces a trade-off between model performance and computational/memory complexity. For some…

Mixed-precision quantization is a powerful tool to enable memory and compute savings of neural network workloads by deploying different sets of bit-width precisions on separate compute operations. In this work, we present a flexible and…

Ant Colony Optimization (ACO) is renowned for its effectiveness in solving Traveling Salesman Problems, yet it faces computational challenges in CPU-based environments, particularly with large-scale instances. In response, we introduce a…

Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algorithm based on tensor decomposition for guaranteed training of…

While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…

Neural architecture search (NAS) has emerged as a promising avenue for automatically designing task-specific neural networks. Existing NAS approaches require one complete search for each deployment specification of hardware or objective.…

In this work, we tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents and increasingly challenging environments. Unlike previous open-ended approaches that optimize agents using a fixed neural…

Ternary quantization has emerged as a powerful technique for reducing both computational and memory footprint of large language models (LLM), enabling efficient real-time inference deployment without significantly compromising model…

Designing neural networks typically relies on manual trial and error or a neural architecture search (NAS) followed by weight training. The former is time-consuming and labor-intensive, while the latter often discretizes architecture search…

Animals ranging from rats to humans can demonstrate cognitive map capabilities. We evolved weights in a biologically plausible recurrent neural network (RNN) using an evolutionary algorithm to replicate the behavior and neural activity…

Evolving neural network architectures is a computationally demanding process. Traditional methods often require an extensive search through large architectural spaces and offer limited understanding of how structural modifications influence…

Existing convolution techniques in artificial neural networks suffer from huge computation complexity, while the biological neural network works in a much more powerful yet efficient way. Inspired by the biological plasticity of dendritic…

In recent years, convolutional neural networks (CNNs) have shown great performance in various fields such as image classification, pattern recognition, and multi-media compression. Two of the feature properties, local connectivity and…

We propose the APTx Neuron, a novel, unified neural computation unit that integrates non-linear activation and linear transformation into a single trainable expression. The APTx Neuron is derived from the APTx activation function, thereby…

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…