Related papers: Continuous Cartesian Genetic Programming based rep…

Convolutional neural networks (CNN) have led to many state-of-the-art results spanning through various fields. However, a clear and profound theoretical understanding of the forward pass, the core algorithm of CNN, is still lacking. In…

Generative adversarial networks (GANs) achieved relevant advances in the field of generative algorithms, presenting high-quality results mainly in the context of images. However, GANs are hard to train, and several aspects of the model…

Monumental advances in deep learning have led to unprecedented achievements across various domains. While the performance of deep neural networks is indubitable, the architectural design and interpretability of such models are nontrivial.…

Gravitational-wave detection strategies are based on a signal analysis technique known as matched filtering. Despite the success of matched filtering, due to its computational cost, there has been recent interest in developing deep…

Multi-omic datasets offer opportunities for improved biomarker discovery in cancer research, but their high dimensionality and limited sample sizes make identifying compact and effective biomarker panels challenging. Feature selection in…

The goals of this research were to search for Convolutional Neural Network (CNN) architectures, suitable for an on-device processor with limited computing resources, performing at substantially lower Network Architecture Search (NAS) costs.…

In this paper, we propose an efficient NAS algorithm for generating task-specific models that are competitive under multiple competing objectives. It comprises of two surrogates, one at the architecture level to improve sample efficiency…

Binary Convolutional Neural Networks (CNNs) have significantly reduced the number of arithmetic operations and the size of memory storage needed for CNNs, which makes their deployment on mobile and embedded systems more feasible. However,…

In recent years, the CNN architectures designed by evolution algorithms have proven to be competitive with handcrafted architectures designed by experts. However, these algorithms need a lot of computational power, which is beyond the…

Performing analytical tasks over graph data has become increasingly interesting due to the ubiquity and large availability of relational information. However, unlike images or sentences, there is no notion of sequence in networks. Nodes…

While state-of-the-art development in CNN topology, such as VGGNet and ResNet, have become increasingly accurate, these networks are computationally expensive involving billions of arithmetic operations and parameters. To improve the…

The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…

Machine learning has rapidly evolved during the last decade, achieving expert human performance on notoriously challenging problems such as image classification. This success is partly due to the re-emergence of bio-inspired modern…

Neural architecture search (NAS) automates neural network design, improving efficiency over manual approaches. However, efficiently discovering high-performance neural network architectures that simultaneously optimize multiple objectives…

Neural Architecture Search (NAS) is a research field concerned with utilizing optimization algorithms to design optimal neural network architectures. There are many approaches concerning the architectural search spaces, optimization…

Predicting protein secondary structure is essential for understanding protein function and advancing drug discovery. However, the intricate sequence-structure relationship poses significant challenges for accurate modeling. To address…

In literature, Clustered Shortest-Path Tree Problem (CluSPT) is an NP-hard problem. Previous studies often search for an optimal solution in relatively large space. To enhance the performance of the search process, two approaches are…

Finding a globally optimal Bayesian Network using exhaustive search is a problem with super-exponential complexity, which severely restricts the number of variables that it can work for. We implement a dynamic programming based algorithm…

In the field of complex action recognition in videos, the quality of the designed model plays a crucial role in the final performance. However, artificially designed network structures often rely heavily on the researchers' knowledge and…

Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is…