Related papers: CARS: Continuous Evolution for Efficient Neural Ar…

Neural Architecture Search (NAS), the process of automating architecture engineering, is an appealing next step to advancing end-to-end Automatic Speech Recognition (ASR), replacing expert-designed networks with learned, task-specific…

Neural Architecture Search has achieved state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, many assumptions, that require human definition, related with the problems being solved or the…

Neural Architecture Search (NAS) refers to automatically design the architecture. We propose an hourglass-inspired approach (HourNAS) for this problem that is motivated by the fact that the effects of the architecture often proceed from the…

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,…

Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges: (1) overcome the catastrophic forgetting problem, (2) adapt…

Neural Architecture Search (NAS) yields state-of-the-art neural networks that outperform their best manually-designed counterparts. However, previous NAS methods search for architectures under one set of training hyper-parameters (i.e., a…

Evolution-based neural architecture search requires high computational resources, resulting in long search time. In this work, we propose a framework of applying the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to the neural…

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.…

Neural architecture search (NAS) enables finding the best-performing architecture from a search space automatically. Most NAS methods exploit an over-parameterized network (i.e., a supernet) containing all possible architectures (i.e.,…

The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the…

The hyper-parameters of a neural network are traditionally designed through a time consuming process of trial and error that requires substantial expert knowledge. Neural Architecture Search (NAS) algorithms aim to take the human out of the…

Early neural network architectures were designed by so-called "grad student descent". Since then, the field of Neural Architecture Search (NAS) has developed with the goal of algorithmically designing architectures tailored for a dataset of…

Edge computing aims to enable edge devices, such as IoT devices, to process data locally instead of relying on the cloud. However, deep learning techniques like computer vision and natural language processing can be computationally…

Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this work, in order to help ground the empirical results in this…

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however,…

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…

Deep convolutional neural networks demonstrate impressive results in the super-resolution domain. A series of studies concentrate on improving peak signal noise ratio (PSNR) by using much deeper layers, which are not friendly to constrained…

We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP). We show that evolutionary search can…

Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation. However, more recent works find that…

Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal…