Related papers: Analyzing the Expected Hitting Time of Evolutionar…
Neural network architecture search provides a solution to the automatic design of network structures. However, it is difficult to search the whole network architecture directly. Although using stacked cells to search neural network…
Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into the…
Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate operations. In Early-Exiting Neural Networks (EENN), exit…
Recent advances in Neural Architecture Search (NAS) such as one-shot NAS offer the ability to extract specialized hardware-aware sub-network configurations from a task-specific super-network. While considerable effort has been employed…
Energy consumption from the selection, training, and deployment of deep learning models has seen a significant uptick recently. This work aims to facilitate the design of energy-efficient deep learning models that require less computational…
One-shot methods have significantly advanced the field of neural architecture search (NAS) by adopting weight-sharing strategy to reduce search costs. However, the accuracy of performance estimation can be compromised by co-adaptation.…
Evolutionary multi-agent systems (EMASs) are very good at dealing with difficult, multi-dimensional problems, their efficacy was proven theoretically based on analysis of the relevant Markov-Chain based model. Now the research continues on…
Neural architecture search (NAS) has emerged as a powerful paradigm that enables researchers to automatically explore vast search spaces and discover efficient neural networks. However, NAS suffers from a critical bottleneck, i.e. the…
Neural architecture search (NAS) aims to automate architecture design processes and improve the performance of deep neural networks. Platform-aware NAS methods consider both performance and complexity and can find well-performing…
Randomized search heuristics such as evolutionary algorithms are frequently applied to dynamic combinatorial optimization problems. Within this paper, we present a dynamic model of the classic Weighted Vertex Cover problem and analyze the…
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…
Recently proposed neural architecture search (NAS) algorithms adopt neural predictors to accelerate the architecture search. The capability of neural predictors to accurately predict the performance metrics of neural architecture is…
Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the…
Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins. Although computationally efficient, their design is often very…
Time series forecasting (TSF) is one of the most important tasks in data science given the fact that accurate time series (TS) predictive models play a major role across a wide variety of domains including finance, transportation, health…
Approximate Nearest Neighbour (ANN) search is a fundamental problem in information retrieval, underpinning large-scale applications in computer vision, natural language processing, and cross-modal search. Hashing-based methods provide an…
Known as two cornerstones of problem solving by search, exploitation and exploration are extensively discussed for implementation and application of evolutionary algorithms (EAs). However, only a few researches focus on evaluation and…
Different from other deep scalable architecture-based NAS approaches, Broad Neural Architecture Search (BNAS) proposes a broad scalable architecture which consists of convolution and enhancement blocks, dubbed Broad Convolutional Neural…
This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we present EVAS, a new attack that leverages NAS to find…
Neural Architecture Search (NAS) achieves significant progress in many computer vision tasks. While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating…