Related papers: ELENA: Epigenetic Learning through Evolved Neural …

Evolutionary Computation (EC) has been shown to be able to quickly train Deep Artificial Neural Networks (DNNs) to solve Reinforcement Learning (RL) problems. While a Genetic Algorithm (GA) is well-suited for exploiting reward functions…

The performance of evolutionary algorithms can be heavily undermined when constraints limit the feasible areas of the search space. For instance, while Covariance Matrix Adaptation Evolution Strategy is one of the most efficient algorithms…

Recurrent neural networks are good at solving prediction problems. However, finding a network that suits a problem is quite hard because their performance is strongly affected by their architecture configuration. Automatic architecture…

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…

Traffic Engineering (TE) in large-scale networks like cloud Wide Area Networks (WANs) and Low Earth Orbit (LEO) satellite constellations is a critical challenge. Although learning-based approaches have been proposed to address the…

Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different structures, recent methods design dynamic structures adapted…

Genetic algorithms are a well-known example of bio-inspired heuristic methods. They mimic natural selection by modeling several operators such as mutation, crossover, and selection. Recent discoveries about Epigenetics regulation processes…

Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…

Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a…

Information networks are ubiquitous and are ideal for modeling relational data. Networks being sparse and irregular, network embedding algorithms have caught the attention of many researchers, who came up with numerous embeddings algorithms…

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…

Feature interaction selection is a fundamental problem in commercial recommender systems. Most approaches equally enumerate all features and interactions by the same pre-defined operation under expert guidance. Their recommendation is…

Evolutionary algorithms (EAs) have emerged as a powerful framework for optimization, especially for black-box optimization. Existing evolutionary algorithms struggle to comprehend and effectively utilize task-specific information for…

Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of…

Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or…

In Programming by Demonstration, the robot learns novel skills from human demonstrations. After learning, the robot should be able not only to reproduce the skill, but also to generalize it to shifted domains without collecting new training…

Evolutionary algorithms (EAs) have achieved remarkable success in tackling complex combinatorial optimization problems. However, EAs often demand carefully-designed operators with the aid of domain expertise to achieve satisfactory…

Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances. This paper…

Generative adversarial networks (GAN) have been effective for learning generative models for real-world data. However, existing GANs (GAN and its variants) tend to suffer from training problems such as instability and mode collapse. In this…

Designing RNA molecules has garnered recent interest in medicine, synthetic biology, biotechnology and bioinformatics since many functional RNA molecules were shown to be involved in regulatory processes for transcription, epigenetics and…