Search Results for author: Ran El-Yaniv

Found 32 papers, 8 papers with code

Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

no code implementations18 Jul 2021 Shai Ben-Assayag, Ran El-Yaniv

Our ScalableAlphaZero is capable of learning to play incrementally on small boards, and advancing to play on large ones.

Board Games Incremental Learning

HydroNets: Leveraging River Structure for Hydrologic Modeling

no code implementations1 Jul 2020 Zach Moshe, Asher Metzger, Gal Elidan, Frederik Kratzert, Sella Nevo, Ran El-Yaniv

In this work we present a novel family of hydrologic models, called HydroNets, which leverages river network structure.

DNF-Net: A Neural Architecture for Tabular Data

no code implementations11 Jun 2020 Ami Abutbul, Gal Elidan, Liran Katzir, Ran El-Yaniv

A challenging open question in deep learning is how to handle tabular data.

Feature Selection

Accurate Hydrologic Modeling Using Less Information

no code implementations21 Nov 2019 Guy Shalev, Ran El-Yaniv, Daniel Klotz, Frederik Kratzert, Asher Metzger, Sella Nevo

Joint models are a common and important tool in the intersection of machine learning and the physical sciences, particularly in contexts where real-world measurements are scarce.

MadNet: Using a MAD Optimization for Defending Against Adversarial Attacks

no code implementations3 Nov 2019 Shai Rozenberg, Gal Elidan, Ran El-Yaniv

Given a deep neural network (DNN) for a classification problem, an application of MAD optimization results in MadNet, a version of the original network, now equipped with an adversarial defense mechanism.

Adversarial Defense

Leveraging Auxiliary Text for Deep Recognition of Unseen Visual Relationships

no code implementations27 Oct 2019 Gal Sadeh Kenigsfield, Ran El-Yaniv

Our model relies on a shared text--image representation of subject-verb-object relationships appearing in the text, and object interactions in images.

Graph Generation Scene Graph Generation +2

ML for Flood Forecasting at Scale

no code implementations28 Jan 2019 Sella Nevo, Vova Anisimov, Gal Elidan, Ran El-Yaniv, Pete Giencke, Yotam Gigi, Avinatan Hassidim, Zach Moshe, Mor Schlesinger, Guy Shalev, Ajai Tirumali, Ami Wiesel, Oleg Zlydenko, Yossi Matias

We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.

SelectiveNet: A Deep Neural Network with an Integrated Reject Option

1 code implementation26 Jan 2019 Yonatan Geifman, Ran El-Yaniv

We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option.

Classification General Classification

Deep Active Learning over the Long Tail

no code implementations2 Nov 2017 Yonatan Geifman, Ran El-Yaniv

This paper is concerned with pool-based active learning for deep neural networks.

Active Learning

Growth-Optimal Portfolio Selection under CVaR Constraints

no code implementations27 May 2017 Guy Uziel, Ran El-Yaniv

Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth.

Decision Making

The Prediction Advantage: A Universally Meaningful Performance Measure for Classification and Regression

no code implementations23 May 2017 Ran El-Yaniv, Yonatan Geifman, Yair Wiener

We introduce the Prediction Advantage (PA), a novel performance measure for prediction functions under any loss function (e. g., classification or regression).

Classification General Classification +1

The Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient

no code implementations19 Mar 2017 Roei Gelbhart, Ran El-Yaniv

We focus on the agnostic setting, for which there is a known algorithm called LESS that learns a PCS classifier and achieves a fast rejection rate (depending on Hanneke's disagreement coefficient) under strong assumptions.

Active Learning General Classification

Multi-Objective Non-parametric Sequential Prediction

no code implementations NeurIPS 2017 Guy Uziel, Ran El-Yaniv

Recently, an algorithm for dealing with several objective functions in the i. i. d.

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision

no code implementations4 Dec 2016 Bar Hilleli, Ran El-Yaniv

We propose a scheme for training a computerized agent to perform complex human tasks such as highway steering.

Imitation Learning

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

5 code implementations22 Sep 2016 Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits.

Online Learning of Commission Avoidant Portfolio Ensembles

no code implementations3 May 2016 Guy Uziel, Ran El-Yaniv

We present a novel online ensemble learning strategy for portfolio selection.

Ensemble Learning

Online Learning of Portfolio Ensembles with Sector Exposure Regularization

no code implementations12 Apr 2016 Guy Uziel, Ran El-Yaniv

We consider online learning of ensembles of portfolio selection algorithms and aim to regularize risk by encouraging diversification with respect to a predefined risk-driven grouping of stocks.

Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

23 code implementations9 Feb 2016 Matthieu Courbariaux, Itay Hubara, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time.

Learn on Source, Refine on Target:A Model Transfer Learning Framework with Random Forests

1 code implementation4 Nov 2015 Noam Segev, Maayan Harel, Shie Mannor, Koby Crammer, Ran El-Yaniv

We propose novel model transfer-learning methods that refine a decision forest model M learned within a "source" domain using a training set sampled from a "target" domain, assumed to be a variation of the source.

Transfer Learning

A Compression Technique for Analyzing Disagreement-Based Active Learning

no code implementations5 Apr 2014 Yair Wiener, Steve Hanneke, Ran El-Yaniv

We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size.

Active Learning

Transductive Rademacher Complexity and its Applications

no code implementations15 Jan 2014 Ran El-Yaniv, Dmitry Pechyony

We develop a technique for deriving data-dependent error bounds for transductive learning algorithms based on transductive Rademacher complexity.

Semantic Sort: A Supervised Approach to Personalized Semantic Relatedness

no code implementations10 Nov 2013 Ran El-Yaniv, David Yanay

We propose and study a novel supervised approach to learning statistical semantic relatedness models from subjectively annotated training examples.

Pointwise Tracking the Optimal Regression Function

no code implementations NeurIPS 2012 Yair Wiener, Ran El-Yaniv

This paper examines the possibility of a `reject option' in the context of least squares regression.

Selective Prediction of Financial Trends with Hidden Markov Models

no code implementations NeurIPS 2011 Dmitry Pidan, Ran El-Yaniv

Our results indicate that both methods are effective, and that the sHMM model is superior.

Agnostic Selective Classification

no code implementations NeurIPS 2011 Yair Wiener, Ran El-Yaniv

For a learning problem whose associated excess loss class is $(\beta, B)$-Bernstein, we show that it is theoretically possible to track the same classification performance of the best (unknown) hypothesis in our class, provided that we are free to abstain from prediction in some region of our choice.

Classification General Classification

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