paper-with-me

홈 › Papers

The SWAG Algorithm; a Mathematical Approach that Outperforms Traditional Deep Learning. Theory and Implementation

2018-11-28 · Saeid Safaei, Vahid Safaei, Solmazi Safaei, Zerotti Woods, Hamid R. Arabnia, Juan B. Gutierrez

The performance of artificial neural networks (ANNs) is influenced by weight initialization, the nature of activation functions, and their architecture. There is a wide range of activation functions that are traditionally used to train a neural network, e.g. sigmoid, tanh, and Rectified Linear Unit (ReLU). A widespread practice is to use the same type of activation function in all neurons in a given layer. In this manuscript, we present a type of neural network in which the activation functions in every layer form a polynomial basis; we name this method SWAG after the initials of the last names of the authors. We tested SWAG on three complex highly non-linear functions as well as the MNIST handwriting data set. SWAG outperforms and converges faster than the state of the art performance in fully connected neural networks. Given the low computational complexity of SWAG, and the fact that it was capable of solving problems current architectures cannot, it has the potential to change the way that we approach deep learning.

📄 PDF Abstract BibTeX arXiv:1811.11813

Code (1)

DeepLearningSaeid/New-Type-of-Deep-Learning 공식 구현

Tasks

Learning Theory

Similar Papers 제목 키워드 기반

Self-Wearing Adaptive Garments via Soft Robotic Unfurling

2025-07-09 · Nam Gyun Kim, William E. Heap, Yimeng Qin, Elvy B. Yao 외 arxiv

Robotic dressing assistance has the potential to improve the quality of life for individuals with limited mobility. Existing solutions predominantly rely on rigid robotic manipulators, which have challenges in handling d…

SWAG: Item Recommendations using Convolutions on Weighted Graphs

2019-11-22 · Amit Pande, Kai Ni, Venkataramani Kini

Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. In this work, we present a Graph Convolutional Network (GCN) algorithm SWAG…

Recommendation Systems

SWAGex at SemEval-2020 Task 4: Commonsense Explanation as Next Event Prediction

2020-12-01 · SEMEVAL 2020 · Wiem Ben Rim, Naoaki Okazaki

We describe the system submitted by the SWAGex team to the SemEval-2020 Commonsense Validation and Explanation Task. We use multiple methods on the pre-trained language model BERT (Devlin et al., 2018) for tasks that req…

Language ModelingLanguage Modelling

SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation

2024-12-25 · Maxence Boels, Yang Liu, Prokar Dasgupta, Alejandro Granados 외

While existing recognition approaches excel at identifying current surgical phases, they provide limited foresight into future procedural steps, restricting their intraoperative utility. Similarly, current anticipation m…

ClassificationLong Term AnticipationPass Classificationregression

SWAG: Storytelling With Action Guidance

2024-02-05 · Zeeshan Patel, Karim El-Refai, Jonathan Pei, Tianle Li

Automated long-form story generation typically employs long-context large language models (LLMs) for one-shot creation, which can produce cohesive but not necessarily engaging content. We introduce Storytelling With Acti…

Story Generation