English
Related papers

Related papers: ActNAS : Generating Efficient YOLO Models using Ac…

200 papers

Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS are determined by…

Machine Learning · Statistics 2020-02-25 D. Kafka , Daniel. N. Wilke

Despite the unresolved 'dying ReLU problem', the classical ReLU activation function (AF) has been extensively applied in Deep Neural Networks (DNN), in particular Convolutional Neural Networks (CNN), for image classification. The common…

Machine Learning · Computer Science 2021-04-30 Stamatis Mastromichalakis

In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has been a renovated interest of the scientific community in…

Machine Learning · Computer Science 2021-03-01 Andrea Apicella , Francesco Donnarumma , Francesco Isgrò , Roberto Prevete

Neural networks have proven to be a highly effective tool for solving complex problems in many areas of life. Recently, their importance and practical usability have further been reinforced with the advent of deep learning. One of the…

Machine Learning · Computer Science 2024-02-15 Vladimír Kunc , Jiří Kléma

Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the…

Optics · Physics 2023-11-03 Guanting Liu , Yiwei Shen , Ruiqian Li , Jingyi Yu , Xuming He , Cheng Wang

Linear Regression and neural networks are widely used to model data. Neural networks distinguish themselves from linear regression with their use of activation functions that enable modeling nonlinear functions. The standard argument for…

Machine Learning · Computer Science 2024-01-02 Anish Lakkapragada

Artificial neural networks typically have a fixed, non-linear activation function at each neuron. We have designed a novel form of piecewise linear activation function that is learned independently for each neuron using gradient descent.…

Neural and Evolutionary Computing · Computer Science 2015-04-22 Forest Agostinelli , Matthew Hoffman , Peter Sadowski , Pierre Baldi

The choice of neural network features can have a large impact on both the accuracy and speed of the network. Despite the current industry shift towards large transformer models, specialized binary classifiers remain critical for numerous…

Neural and Evolutionary Computing · Computer Science 2025-03-17 Benjamin David Winter , William John Teahan

We analyze a simple one-hidden-layer neural network with ReLU activation functions and fixed biases, with one-dimensional input and output. We study both continuous and discrete versions of the model, and we rigorously prove the convergence…

Machine Learning · Computer Science 2026-04-10 Fabricio Macià , Shu Nakamura

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the…

Machine Learning · Computer Science 2019-10-01 Farnoush Farhadi , Vahid Partovi Nia , Andrea Lodi

Activation functions introduce nonlinearity into deep neural networks. Most popular activation functions allow positive values to pass through while blocking or suppressing negative values. From the idea that positive values and negative…

Neural and Evolutionary Computing · Computer Science 2024-07-30 Junjia Chen , Zhibin Pan

With the advancement of Deep Neural Networks (DNN) and large amounts of sensor data from Internet of Things (IoT) systems, the research community has worked to reduce the computational and resource demands of DNN to compute on low-resourced…

Machine Learning · Computer Science 2022-03-09 Young D. Kwon , Jagmohan Chauhan , Cecilia Mascolo

Well-known activation functions like ReLU or Leaky ReLU are non-differentiable at the origin. Over the years, many smooth approximations of ReLU have been proposed using various smoothing techniques. We propose new smooth approximations of…

Machine Learning · Computer Science 2021-09-28 Koushik Biswas , Sandeep Kumar , Shilpak Banerjee , Ashish Kumar Pandey

Active Learning (AL) aims to reduce annotation costs by strategically selecting the most informative samples for labeling. However, most active learning methods struggle in the low-budget regime where only a few labeled examples are…

Machine Learning · Computer Science 2025-04-08 Netta Shafir , Guy Hacohen , Daphna Weinshall

This paper implements and analyzes multiple networks with the goal of understanding their suitability for edge device applications such as X-ray threat detection. In this study, we use the state-of-the-art YOLO object detection model to…

Neural and Evolutionary Computing · Computer Science 2023-11-08 Raghav Ambati , Ayon Borthakur

The rapid advancement in AI architectures and the proliferation of AI-enabled systems have intensified the need for domain-specific architectures that enhance both the acceleration and energy efficiency of AI inference, particularly at the…

Hardware Architecture · Computer Science 2025-12-30 Soham Pramanik , Vimal William , Arnab Raha , Debayan Das , Amitava Mukherjee , Janet L. Paluh

We propose \textbf{ULU}, a novel non-monotonic, piecewise activation function defined as $\{f(x;\alpha_1),x<0; f(x;\alpha_2),x>=0 \}$, where $f(x;\alpha)=0.5x(tanh(\alpha x)+1),\alpha >0$. ULU treats positive and negative inputs…

Machine Learning · Computer Science 2025-08-08 Simin Huo

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning…

Machine Learning · Computer Science 2023-06-06 Mohammad Loni , Aditya Mohan , Mehdi Asadi , Marius Lindauer

Architectures obtained by Neural Architecture Search (NAS) have achieved highly competitive performance in various computer vision tasks. However, the prohibitive computation demand of forward-backward propagation in deep neural networks…

Machine Learning · Computer Science 2019-08-15 Xiawu Zheng , Rongrong Ji , Lang Tang , Baochang Zhang , Jianzhuang Liu , Qi Tian

Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions. However, existing NAS algorithms usually compromise on restricted search space and search on…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Xiong Zhang , Hongmin Xu , Hong Mo , Jianchao Tan , Cheng Yang , Lei Wang , Wenqi Ren