Search Results for author: Shai Fine

Found 6 papers, 2 papers with code

The IDC System for Sentiment Classification and Sarcasm Detection in Arabic

no code implementations EACL (WANLP) 2021 Abraham Israeli, Yotam Nahum, Shai Fine, Kfir Bar

In this paper we present designated solutions for sentiment classification and sarcasm detection tasks that were introduced as part of a shared task by Abu Farha et al. (2021).

Sarcasm Detection Sentiment Analysis +1

Pairwise Margin Maximization for Deep Neural Networks

1 code implementation9 Oct 2021 Berry Weinstein, Shai Fine, Yacov Hel-Or

The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization.

Multi-class Classification

Margin-Based Regularization and Selective Sampling in Deep Neural Networks

no code implementations13 Sep 2020 Berry Weinstein, Shai Fine, Yacov Hel-Or

We derive a new margin-based regularization formulation, termed multi-margin regularization (MMR), for deep neural networks (DNNs).

General Classification Image Classification +7

Selective sampling for accelerating training of deep neural networks

1 code implementation16 Nov 2019 Berry Weinstein, Shai Fine, Yacov Hel-Or

We present a selective sampling method designed to accelerate the training of deep neural networks.

Binary Classification Classification +2

Actigraphy-based Sleep/Wake Pattern Detection using Convolutional Neural Networks

no code implementations22 Feb 2018 Lena Granovsky, Gabi Shalev, Nancy Yacovzada, Yotam Frank, Shai Fine

In order to study the connection between sleep/wake patterns and a cluster headache disorder, activity data was collected using a wearable device in the course of a clinical trial.

Management Multi-Task Learning +3

On the Blindspots of Convolutional Networks

no code implementations14 Feb 2018 Elad Hoffer, Shai Fine, Daniel Soudry

Deep convolutional network has been the state-of-the-art approach for a wide variety of tasks over the last few years.

Cannot find the paper you are looking for? You can Submit a new open access paper.