Training state-of-the-art neural networks requires a high cost in terms ...
A standard ML model is commonly generated by a single method that specif...
The traditional ML development methodology does not enable a large numbe...
The traditional Machine Learning (ML) methodology requires to fragment t...
Multitask learning assumes that models capable of learning from multiple...
Most uses of machine learning today involve training a model from scratc...
Recent neural network-based language models have benefited greatly from
...
The core challenge with continual learning is catastrophic forgetting, t...
Neural architecture search has recently attracted lots of research effor...
This paper proposes a novel per-task routing method for multi-task
appli...
The timing of individual neuronal spikes is essential for biological bra...
Recent advances in Neural Architecture Search (NAS) have produced
state-...
Neural architecture search has been shown to hold great promise towards ...
Fine-tuning large pre-trained models is an effective transfer mechanism ...
Neural architecture search (NAS) enabled the discovery of state-of-the-a...
Neural Architecture Search has recently shown potential to automate the
...
Building effective neural networks requires many design choices. These
i...
We analyze the language learned by an agent trained with reinforcement
l...
Deep learning models require extensive architecture design exploration a...
We frame Question Answering as a Reinforcement Learning task, an approac...