paper-with-me

홈 › Papers

Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics

2016-11-01 · Jay M. Wong

Despite outstanding success in vision amongst other domains, many of the recent deep learning approaches have evident drawbacks for robots. This manuscript surveys recent work in the literature that pertain to applying deep learning systems to the robotics domain, either as means of estimation or as a tool to resolve motor commands directly from raw percepts. These recent advances are only a piece to the puzzle. We suggest that deep learning as a tool alone is insufficient in building a unified framework to acquire general intelligence. For this reason, we complement our survey with insights from cognitive development and refer to ideas from classical control theory, producing an integrated direction for a lifelong learning architecture.

📄 PDF Abstract BibTeX arXiv:1611.00201

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningLifelong learning

Similar Papers 제목 키워드 기반

SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge

2022-08-24 · Xiaofan Yu, Yunhui Guo, Sicun Gao, Tajana Rosing

Unsupervised lifelong learning refers to the ability to learn over time while memorizing previous patterns without supervision. Although great progress has been made in this direction, existing work often assumes strong …

Lifelong learning

The Empirical Impact of Forgetting and Transfer in Continual Visual Odometry

2024-06-03 · Paolo Cudrano, Xiaoyu Luo, Matteo Matteucci

As robotics continues to advance, the need for adaptive and continuously-learning embodied agents increases, particularly in the realm of assistance robotics. Quick adaptability and long-term information retention are es…

Lifelong learningTransfer LearningVisual Odometry

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation

2020-03-31 · Victor Schmidt, Makesh Narsimhan Sreedhar, Mostafa ElAraby, Irina Rish

Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling. Leveraging auxiliary tasks such a…

ColorizationContinual LearningImage-to-Image TranslationSelf-Supervised Learning+1

Uncertainty-guided Lifelong Learning in Bayesian Networks

2018-09-27 · Sayna Ebrahimi, Mohamed Elhoseiny, Trevor Darrell, Marcus Rohrbach

Sequentially learning of tasks arriving in a continuous stream is a complex problem and becomes more challenging when the model has a fixed capacity. Lifelong learning aims at learning new tasks without forgetting previ…

Continual LearningLifelong learning

Computational Theories of Curiosity-Driven Learning

2018-02-28 · Pierre-Yves Oudeyer

What are the functions of curiosity? What are the mechanisms of curiosity-driven learning? We approach these questions about the living using concepts and tools from machine learning and developmental robotics. We argue …

BIG-bench Machine LearningLifelong learning