English
Related papers

Related papers: Breaking the Activation Function Bottleneck throug…

200 papers

In this work, a method of random parameters generation for randomized learning of a single-hidden-layer feedforward neural network is proposed. The method firstly, randomly selects the slope angles of the hidden neurons activation functions…

Machine Learning · Computer Science 2019-08-16 Grzegorz Dudek

We investigate deep morphological neural networks (DMNNs). We demonstrate that despite their inherent non-linearity, "linear" activations are essential for DMNNs. To preserve their inherent sparsity, we propose architectures that constraint…

Machine Learning · Computer Science 2025-12-24 Konstantinos Fotopoulos , Petros Maragos

A neural network has an activation bottleneck if one of its hidden layers has a bounded image. We show that networks with an activation bottleneck cannot forecast unbounded sequences such as straight lines, random walks, or any sequence…

Machine Learning · Computer Science 2024-06-05 Maximilian Toller , Hussain Hussain , Bernhard C Geiger

Feature learning in neural networks is crucial for their expressive power and inductive biases, motivating various theoretical approaches. Some approaches describe network behavior after training through a change in kernel scale from…

Disordered Systems and Neural Networks · Physics 2025-05-29 Noa Rubin , Kirsten Fischer , Javed Lindner , David Dahmen , Inbar Seroussi , Zohar Ringel , Michael Krämer , Moritz Helias

Addressing the imperative need for efficient artificial intelligence in IoT and edge computing, this study presents RepAct, a re-parameterizable adaptive activation function tailored for optimizing lightweight neural networks within the…

Machine Learning · Computer Science 2024-07-02 Xian Wu , Qingchuan Tao , Shuang Wang

Spiking Neural Networks (SNNs) have emerged as an attractive spatio-temporal computing paradigm for complex vision tasks. However, most existing works yield models that require many time steps and do not leverage the inherent temporal…

Neural and Evolutionary Computing · Computer Science 2022-10-25 Gourav Datta , Haoqin Deng , Robert Aviles , Peter A. Beerel

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult…

Computer Vision and Pattern Recognition · Computer Science 2014-11-20 Qian Wang , Jiaxing Zhang , Sen Song , Zheng Zhang

Tree-structured neural networks encode a particular tree geometry for a sentence in the network design. However, these models have at best only slightly outperformed simpler sequence-based models. We hypothesize that neural sequence models…

Computation and Language · Computer Science 2015-11-10 Samuel R. Bowman , Christopher D. Manning , Christopher Potts

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less…

Machine Learning · Computer Science 2022-06-07 Carles Riera , Camilo Rey , Thiago Serra , Eloi Puertas , Oriol Pujol

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks by understanding input information and predicting corresponding outputs. However, the internal mechanisms by which LLMs comprehend input and…

Computation and Language · Computer Science 2025-01-07 Zhou Yang , Zhengyu Qi , Zhaochun Ren , Zhikai Jia , Haizhou Sun , Xiaofei Zhu , Xiangwen Liao

Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches. As a widely applied powerful technique in…

Computation and Language · Computer Science 2024-04-24 Yang Tan , Mingchen Li , Bingxin Zhou , Bozitao Zhong , Lirong Zheng , Pan Tan , Ziyi Zhou , Huiqun Yu , Guisheng Fan , Liang Hong

Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and…

Machine Learning · Computer Science 2022-01-25 Garrett Bingham , Risto Miikkulainen

Activation in deep neural networks is fundamental to achieving non-linear mappings. Traditional studies mainly focus on finding fixed activations for a particular set of learning tasks or model architectures. The research on flexible…

Neural and Evolutionary Computing · Computer Science 2020-08-20 Renlong Jie , Junbin Gao , Andrey Vasnev , Min-ngoc Tran

Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on…

The calibration and training of a neural network is a complex and time-consuming procedure that requires significant computational resources to achieve satisfactory results. Key obstacles are a large number of hyperparameters to select and…

Machine Learning · Computer Science 2023-09-07 Raffaele Giuseppe Cestari , Gabriele Maroni , Loris Cannelli , Dario Piga , Simone Formentin

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise…

Machine Learning · Computer Science 2020-10-16 Fanghui Liu , Xiaolin Huang , Chen Gong , Jie Yang , Li Li

Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs). In practice, LLMs are often required to handle a diverse set of tasks from multiple domains, a scenario naturally addressed by multi-task…

Computation and Language · Computer Science 2025-08-08 Jinda Liu , Bo Cheng , Yi Chang , Yuan Wu

Convolutional neural networks model the transformation of the input sensory data at the bottom of a network hierarchy to the semantic information at the top of the visual hierarchy. Feedforward processing is sufficient for some object…

Computer Vision and Pattern Recognition · Computer Science 2020-02-05 Mahdi Biparva , John Tsotsos

Concept bottleneck models (CBMs) improve neural network interpretability by introducing an intermediate layer that maps human-understandable concepts to predictions. Recent work has explored the use of vision-language models (VLMs) to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Xingbo Du , Qiantong Dou , Lei Fan , Rui Zhang