natural-language-processing-10

Self-Learning

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in self-learning-10

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find self-learning-10 models and implementations

Datasets

LEARNING STYLE IDENTIFICATION

Subtasks

No subtasks available.

Most implemented papers

Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments

H. Surmann, Christian Jestel, Robin Marchel, Franziska Musberg, Houssem Elhadj, Mahbube Ardani•Wed May 27 2020

This paper presents the proof of concept for autonomous self-learning robot navigation in an unknown environment for a real robot without a map or planner and trains on environments of varying difficulties and run 32 training instances simultaneously to increase the robustness.

99

Content

0

Paper Graph

Domain Adaptation Without Source Data

Youngeun Kim, P. Panda, Kyeongtak Han, Sungeun Hong•Thu Jul 02 2020

Based on the privacy-preserving domain adaptation, various stakeholders, including enterprises and government organizations, can be free of concern about privacy issues with their labeled source dataset, and the proposed data-free approach can contribute to creating a positive social impact, especially in large-scale datasets.

211 0

Paper Graph

Learning Program Synthesis for Integer Sequences from Scratch

Thibault Gauthier, J. Urban•Wed Feb 23 2022

This work presents a self-learning approach for synthesizing programs from integer sequences that relies on a tree search guided by a learned policy and discovers solutions for 27987 sequences starting from basic operators and without human-written training examples.

11 0

Paper Graph

A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings

Eneko Agirre, Mikel Artetxe, Gorka Labaka•Tue May 15 2018

This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution.

610 0

Paper Graph

Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019

Ting Yao, Yingwei Pan, Yehao Li, Yang Chen, Qi Cai•Mon Oct 07 2019

This notebook paper presents an overview and comparative analysis of the systems designed for the following two tasks in Visual Domain Adaptation Challenge (VisDA-2019): multi-source domain adaptation and semi-supervised domain adaptation.

5 0

Paper Graph

Self-Learning Transformations for Improving Gaze and Head Redirection

Xucong Zhang, Seonwook Park, Otmar Hilliges, Shalini De Mello, Yufeng Zheng•Thu Oct 22 2020

A novel generative model for images of faces, that is capable of producing high-quality images under fine-grained control over eye gaze and head orientation angles, and which learns to discover, disentangle and encode these extraneous variations in a self-learned manner is proposed.

46 0

Paper Graph

Knowledge Inheritance for Pre-trained Language Models

Jiajie Zhang, Xu Han, Zhiyuan Liu, Maosong Sun, Peng Li, Jie Zhou, Yujia Qin, Yankai Lin, Zhengyan Zhang, Yusheng Su, Jing Yi•Thu May 27 2021

A pre-training framework named “knowledge inheritance” (KI) is introduced and how could knowledge distillation serve as auxiliary supervision during pre- training to efficiently learn larger PLMs is explored, demonstrating the superiority of KI in training efficiency.

57 0

Paper Graph

Transfer of Pretrained Model Weights Substantially Improves Semi-supervised Image Classification

Attaullah Sahito, E. Frank, Bernhard Pfahringer•Wed Sep 01 2021

It is found that transfer learning always substantially improves the model's accuracy when few labeled examples are available, regardless of the type of loss used for training the neural network.

2 0

Paper Graph

Maximum Bayes Smatch Ensemble Distillation for AMR Parsing

S. Roukos, Radu Florian, Young-Suk Lee, Ramón Fernández Astudillo, T. Hoang, Tahira Naseem•Mon Dec 13 2021

This paper proposes to overcome diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation, and shows that it can produce gains rivaling those of human annotated data for QALD-9 and achieve a new state-of-the-art for BioAMR.

40 0

Paper Graph

Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms

Halil Durmus, Resul Dagdanov, N. K. Ure•Fri Oct 28 2022

Simulation results demonstrate that the proposed self-improving artificial intelligence system efficiently discovers safety failures of action decisions in RL-based adaptive cruise control (ACC) applications and significantly reduces the number of vehicle collisions through iterative applications of the method.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.