Results 61 to 70 of about 1,961,679 (175)
Grounding Language for Transfer in Deep Reinforcement Learning
, 2018 In this paper, we explore the utilization of natural language to drive transfer for reinforcement learning (RL). Despite the wide-spread application of deep RL techniques, learning generalized policy representations that work across domains remains a ...
Barzilay, Regina +2 more
core +1 more source
Transfer learning for radio galaxy classification
, 2019 In the context of radio galaxy classification, most state-of-the-art neural network algorithms have been focused on single survey data. The question of whether these trained algorithms have cross-survey identification ability or can be adapted to develop
Leahy, J. P. +2 more
core +1 more source
On the Feasibility of Transfer-learning Code Smells using Deep Learning
, 2019 Context: A substantial amount of work has been done to detect smells in source code using metrics-based and heuristics-based methods. Machine learning methods have been recently applied to detect source code smells; however, the current practices are ...
Efstathiou, Vasiliki +3 more
core +1 more source
Improving speaker turn embedding by crossmodal transfer learning from face embedding
, 2017 Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which ...
Le, Nam, Odobez, Jean-Marc
core +1 more source
Adaptive Transfer Learning: a simple but effective transfer learning
, 2021 Transfer learning (TL) leverages previously obtained knowledge to learn new tasks efficiently and has been used to train deep learning (DL) models with limited amount of data. When TL is applied to DL, pretrained (teacher) models are fine-tuned to build domain specific (student) models.
Lee, Jung H +9 more
openaire +2 more sources
On universal transfer learning [PDF]
Theoretical Computer Science, 2007 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire +3 more sources
Learning Transfer: The Missing Link to Learning among School Leaders in Burkina Faso and Ghana
Frontiers in Education, 2018 Every year, billions of dollars are spent on development aid and training around the world. However, only 10% of this training results in the transfer of knowledge, skills, or behaviors learned in the training to the work place.
Corinne Brion, Paula A. Cordeiro
doaj +1 more source
Scientific ReportsData sparseness is a major limiting factor for deep machine learning. In the natural sciences, data distributions are heterogeneous. For instance, in chemistry and early-phase drug discovery, compound and molecular property data are typically sparse ...
Antonia Mera +2 more
doaj +1 more source
Mutual Alignment Transfer Learning
, 2017 Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress.
Wulfmeier, M, Posner, H, Abbeel, P
openaire +3 more sources
Domain Transfer Multiple Kernel Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012 Cross-domain learning methods have shown promising results by leveraging labeled patterns from the auxiliary domain to learn a robust classifier for the target domain which has only a limited number of labeled samples. To cope with the considerable change between feature distributions of different domains, we propose a new cross-domain kernel learning ...
Duan, Lixin +2 more
openaire +3 more sources