User:Martijho
From Robin
Line 8: | Line 8: | ||
== Who cites PathNet? == | == Who cites PathNet? == | ||
- | * [https://arxiv.org/pdf/1703.10371.pdf Born to Learn] | + | * '''''[https://arxiv.org/pdf/1703.10371.pdf Born to Learn]''''' |
EPANN - Evolved Plastic Artificial Neural Networks | EPANN - Evolved Plastic Artificial Neural Networks | ||
Mentions Pathnet as an example of where evolution where | Mentions Pathnet as an example of where evolution where | ||
Line 16: | Line 16: | ||
evolution and deep learning approaches. | evolution and deep learning approaches. | ||
- | * [https://arxiv.org/pdf/1706.00046.pdf Learning time-efficient deep architectures with budgeted super networks] | + | * '''''[https://arxiv.org/pdf/1706.00046.pdf Learning time-efficient deep architectures with budgeted super networks]''''' |
Mentions PathNet as a predecessor in the super neural network family | Mentions PathNet as a predecessor in the super neural network family | ||
- | * [https://arxiv.org/pdf/1708.07902.pdf Deep Learning for video game playing] | + | * '''''[https://arxiv.org/pdf/1708.07902.pdf Deep Learning for video game playing]''''' |
Reviewing recent deep learning advances in the context | Reviewing recent deep learning advances in the context | ||
of how they have been applied to play different types of video games | of how they have been applied to play different types of video games | ||
- | *[http://ceur-ws.org/Vol-1958/IOTSTREAMING2.pdf Evolutive deep models for online learning on data streams with no storage] | + | * '''''[http://ceur-ws.org/Vol-1958/IOTSTREAMING2.pdf Evolutive deep models for online learning on data streams with no storage]''''' |
Pathnet is proposed alongside PNNS as a way to deal with changing environments. It is mentioned that both PathNet and progressive networks show good results on sequences of tasks and are a good alternative to fine-tuning to accelerate learning. | Pathnet is proposed alongside PNNS as a way to deal with changing environments. It is mentioned that both PathNet and progressive networks show good results on sequences of tasks and are a good alternative to fine-tuning to accelerate learning. | ||
- | *[https://openreview.net/pdf?id=H1XLbXEtg Online multi-task learning using active sampling] | + | * '''''[https://openreview.net/pdf?id=H1XLbXEtg Online multi-task learning using active sampling]''''' |
Revision as of 13:10, 6 November 2017
PathNet
- Super neural network
- Evolved sub-models from a larger set of parameters
- Multitask learning
- No catastrophic forgetting
- Embedded transfer learning
Who cites PathNet?
EPANN - Evolved Plastic Artificial Neural Networks Mentions Pathnet as an example of where evolution where used to train a network on multiple tasks. "While these results were only possible through significant computational resources, they demonstrate the potential of combining evolution and deep learning approaches.
Mentions PathNet as a predecessor in the super neural network family
Reviewing recent deep learning advances in the context of how they have been applied to play different types of video games
Pathnet is proposed alongside PNNS as a way to deal with changing environments. It is mentioned that both PathNet and progressive networks show good results on sequences of tasks and are a good alternative to fine-tuning to accelerate learning.