Deep convolution neural network sharing for the multi-label images classification
S Coulibaly, B Kamsu-Foguem, D Kamissoko… - Machine learning with …, 2022 - Elsevier
Addressing issues related to multi-label classification is relevant in many fields of
applications. In this work. We present a multi-label classification architecture based on Multi …
applications. In this work. We present a multi-label classification architecture based on Multi …
Deep model reassembly
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …
Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous …
Multi-task learning with deep neural networks: A survey
M Crawshaw - arxiv preprint arxiv:2009.09796, 2020 - arxiv.org
Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are
simultaneously learned by a shared model. Such approaches offer advantages like …
simultaneously learned by a shared model. Such approaches offer advantages like …
Methods for pruning deep neural networks
This paper presents a survey of methods for pruning deep neural networks. It begins by
categorising over 150 studies based on the underlying approach used and then focuses on …
categorising over 150 studies based on the underlying approach used and then focuses on …
Explainable AI in deep reinforcement learning models for power system emergency control
Artificial intelligence (AI) technology has become an important trend to support the analysis
and control of complex and time-varying power systems. Although deep reinforcement …
and control of complex and time-varying power systems. Although deep reinforcement …
Model spider: Learning to rank pre-trained models efficiently
Abstract Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is
essential to take advantage of plentiful model resources. With the availability of numerous …
essential to take advantage of plentiful model resources. With the availability of numerous …
A review on transferability estimation in deep transfer learning
Deep transfer learning has become increasingly prevalent in various fields such as industry
and medical science in recent years. To ensure the successful implementation of target …
and medical science in recent years. To ensure the successful implementation of target …
Task switching network for multi-task learning
Abstract We introduce Task Switching Networks (TSNs), a task-conditioned architecture with
a single unified encoder/decoder for efficient multi-task learning. Multiple tasks are …
a single unified encoder/decoder for efficient multi-task learning. Multiple tasks are …
Explainable AI in deep reinforcement learning models: A shap method applied in power system emergency control
The application of artificial intelligence (AI) system is more and more extensive, using the
explainable AI (XAI) technology to explain why machine learning (ML) models make certain …
explainable AI (XAI) technology to explain why machine learning (ML) models make certain …
Scalable diverse model selection for accessible transfer learning
D Bolya, R Mittapalli, J Hoffman - Advances in Neural …, 2021 - proceedings.neurips.cc
With the preponderance of pretrained deep learning models available off-the-shelf from
model banks today, finding the best weights to fine-tune to your use-case can be a daunting …
model banks today, finding the best weights to fine-tune to your use-case can be a daunting …