Related papers: BioArc: Discovering Optimal Neural Architectures f…

Neural architecture search (NAS) aims to automatically design deep neural networks of satisfactory performance. Wherein, architecture performance predictor is critical to efficiently value an intermediate neural architecture. But for the…

The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key…

Biological nervous systems consist of networks of diverse, sophisticated information processors in the form of neurons of different classes. In most artificial neural networks (ANNs), neural computation is abstracted to an activation…

Neural architecture search has been shown to hold great promise towards the automation of deep learning. However in spite of its potential, neural architecture search remains quite costly. To this point, we propose a novel gradient-based…

Deep neural networks have recently drawn considerable attention to build and evaluate artificial learning models for perceptual tasks. Here, we present a study on the performance of the deep learning models to deal with global optimization…

Neuromorphic computing seeks to replicate the remarkable efficiency, flexibility, and adaptability of the human brain in artificial systems. Unlike conventional digital approaches, which suffer from the Von Neumann bottleneck and depend on…

Catastrophic forgetting has been the leading issue in the domain of lifelong learning in artificial systems. Current artificial systems are reasonably good at learning domains they have seen before; however, as soon as they encounter…

Foundation models can be disruptive for future AI development by scaling up deep learning in terms of model size and training data's breadth and size. These models achieve state-of-the-art performance (often through further adaptation) on a…

In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly…

Searching for the architecture cells is a dominant paradigm in NAS. However, little attention has been devoted to the analysis of the cell-based search spaces even though it is highly important for the continual development of NAS. In this…

Current neural architecture search (NAS) algorithms still require expert knowledge and effort to design a search space for network construction. In this paper, we consider automating the search space design to minimize human interference,…

Cognitive diagnosis plays a vital role in modern intelligent education platforms to reveal students' proficiency in knowledge concepts for subsequent adaptive tasks. However, due to the requirement of high model interpretability, existing…

Architecture search is the process of automatically learning the neural model or cell structure that best suits the given task. Recently, this approach has shown promising performance improvements (on language modeling and image…

Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking…

Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor…

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.…

Brain foundation models (BFMs) have emerged as a transformative paradigm in computational neuroscience, offering a revolutionary framework for processing diverse neural signals across different brain-related tasks. These models leverage…

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…

We propose a vision-based architecture search algorithm for robot manipulation learning, which discovers interactions between low dimension action inputs and high dimensional visual inputs. Our approach automatically designs architectures…

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.…