Self-Learning
54 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Self-Learning
Most implemented papers
Deep Reinforcement learning for real autonomous mobile robot navigation in indoor environments
In this paper we present our proof of concept for autonomous self-learning robot navigation in an unknown environment for a real robot without a map or planner.
Domain Adaptation without Source Data
youngryan1993/SFDA-Domain-Adaptation-without-Source-Data
•
•
Our key idea is to leverage a pre-trained model from the source domain and progressively update the target model in a self-learning manner.
Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019
Panda-Peter/visda2019-multisource
•
•
Semi-Supervised Domain Adaptation: For this task, we adopt a standard self-learning framework to construct a classifier based on the labeled source and target data, and generate the pseudo labels for unlabeled target data.
Self-Learning Transformations for Improving Gaze and Head Redirection
Furthermore, we show that in the presence of limited amounts of real-world training data, our method allows for improvements in the downstream task of semi-supervised cross-dataset gaze estimation.
Knowledge Inheritance for Pre-trained Language Models
thunlp/Knowledge-Inheritance
•
•
Specifically, we introduce a pre-training framework named "knowledge inheritance" (KI) and explore how could knowledge distillation serve as auxiliary supervision during pre-training to efficiently learn larger PLMs.
Maximum Bayes Smatch Ensemble Distillation for AMR Parsing
AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning.
Learning Program Synthesis for Integer Sequences from Scratch
We present a self-learning approach for synthesizing programs from integer sequences.
Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution
The benefit is that for designing cloud controllers, we do not have to rely solely on precise design-time knowledge, which may be difficult to acquire.
End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning
end2you/end2you
•
•
To our knowledge, this is the first toolkit that provides generic end-to-end learning for profiling capabilities in either unimodal or multimodal cases.
A Deep Q-Learning Agent for the L-Game with Variable Batch Training
We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states.
