Related papers: EENA: Efficient Evolution of Neural Architecture
In this paper we introduce two algorithms for neural architecture search (NASGD and NASAGD) following the theoretical work by two of the authors [5] which used the geometric structure of optimal transport to introduce the conceptual basis…
Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state,…
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a…
Neural architecture search (NAS) relies on a good controller to generate better architectures or predict the accuracy of given architectures. However, training the controller requires both abundant and high-quality pairs of architectures…
Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search…
Multiplication is arguably the most cost-dominant operation in modern deep neural networks (DNNs), limiting their achievable efficiency and thus more extensive deployment in resource-constrained applications. To tackle this limitation,…
Deep Convolutional Neural Networks (CNN) provides an "end-to-end" solution for image pattern recognition with impressive performance in many areas of application including medical imaging. Most CNN models of high performance use…
Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…
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…
A variety of methods have been applied to the architectural configuration and learning or training of artificial deep neural networks (DNN). These methods play a crucial role in the success or failure of the DNN for most problems and…
Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary…
Neural architecture search (NAS) has become increasingly popular in the deep learning community recently, mainly because it can provide an opportunity to allow interested users without rich expertise to benefit from the success of deep…
Recently, numerous efficient Transformers have been proposed to reduce the quadratic computational complexity of standard Transformers caused by the Softmax attention. However, most of them simply swap Softmax with an efficient attention…
Neural Architecture Search (NAS) represents a class of methods to generate the optimal neural network architecture and typically iterate over candidate architectures till convergence over some particular metric like validation loss. They…
Data-driven, automatic design space exploration of neural accelerator architecture is desirable for specialization and productivity. Previous frameworks focus on sizing the numerical architectural hyper-parameters while neglect searching…
How to discover and evaluate the true strength of models quickly and accurately is one of the key challenges in Neural Architecture Search (NAS). To cope with this problem, we propose an Architecture-Driven Weight Prediction (ADWP) approach…
In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon target hardware. To…
Deep Evolutionary Network Structured Representation (DENSER) is a novel approach to automatically design Artificial Neural Networks (ANNs) using Evolutionary Computation. The algorithm not only searches for the best network topology (e.g.,…
Finding optimal channel dimensions (i.e., the number of filters in DNN layers) is essential to design DNNs that perform well under computational resource constraints. Recent work in neural architecture search aims at automating the…
Mobile and edge computing devices for always-on classification tasks require energy-efficient neural network architectures. In this paper we present several changes to neural architecture searches (NAS) that improve the chance of success in…