Related papers: GeneSys: Enabling Continuous Learning through Neur…

Edge Artificial Intelligence (Edge AI) embeds intelligence directly into devices at the network edge, enabling real-time processing with improved privacy and reduced latency by processing data close to its source. This review systematically…

Generative artificial intelligence (GenAI) holds the potential to transform the delivery, cultivation, and evaluation of human learning. This Perspective examines the integration of GenAI as a tool for human learning, addressing its…

Continual learning, the ability to acquire and transfer knowledge through a models lifetime, is critical for artificial agents that interact in real-world environments. Biological brains inherently demonstrate these capabilities while…

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample…

Variational Autoencoder (VAE) and its variations are classic generative models by learning a low-dimensional latent representation to satisfy some prior distribution (e.g., Gaussian distribution). Their advantages over GAN are that they can…

Neurons in real brains are enormously complex computational units. Among other things, they're responsible for transforming inbound electro-chemical vectors into outbound action potentials, updating the strengths of intermediate synapses,…

Neuroevolution is a powerful method of applying an evolutionary algorithm to refine the performance of artificial neural networks through natural selection; however, the fitness evaluation of these networks can be time-consuming and…

Variational autoencoder (VAE) is a deep generative model for unsupervised learning, allowing to encode observations into the meaningful latent space. VAE is prone to catastrophic forgetting when tasks arrive sequentially, and only the data…

Most existing training systems focus on a single region. In contrast, we envision that cross-region training offers more flexible GPU resource allocation and yields significant potential. However, the hierarchical cluster topology and…

Variational Autoencoders (VAEs) suffer from degenerated performance, when learning several successive tasks. This is caused by catastrophic forgetting. In order to address the knowledge loss, VAEs are using either Generative Replay (GR)…

Generative Artificial Intelligence (AI) models are a compelling way to introduce K-12 students to AI education using an artistic medium, and hence have drawn attention from K-12 AI educators. Previous Creative AI curricula mainly focus on…

The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample…

For various optimization methods, gradient descent-based algorithms can achieve outstanding performance and have been widely used in various tasks. Among those commonly used algorithms, ADAM owns many advantages such as fast convergence…

Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective…

This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix…

In this tutorial, we explore Variational Autoencoders (VAEs), an essential framework for unsupervised learning, particularly suited for high-dimensional datasets such as neuroimaging. By integrating deep learning with Bayesian inference,…

The disparity between the computational demands of deep learning and the capabilities of compute hardware is expanding drastically. Although deep learning achieves remarkable performance in countless tasks, its escalating requirements for…

Large pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive generalization but remain highly vulnerable to adversarial examples (AEs). Previous work has explored robust text prompts through adversarial training,…

A new model for evolving Evolutionary Algorithms (EAs) is proposed in this paper. The model is based on the Multi Expression Programming (MEP) technique. Each MEP chromosome encodes an evolutionary pattern that is repeatedly used for…

Multi-task reinforcement learning employs a single policy to complete various tasks, aiming to develop an agent with generalizability across different scenarios. Given the shared characteristics of tasks, the agent's learning efficiency can…