Search Results for author:
Found 5 papers, 2 papers with code
Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning
We show that our zapping procedure results in improved transfer accuracy and/or more rapid adaptation in both standard fine-tuning and continual learning settings, while being simple to implement and computationally efficient.
Coping with seasons: evolutionary dynamics of gene networks in a changing environment
In contrast, conservative bet-hedgers have a set of offspring that all have an in-between phenotype compared to the specialists.
A good body is all you need: avoiding catastrophic interference via agent architecture search
Efforts to combat catastrophic interference to date focus on novel neural architectures or training methods, with a recent emphasis on policies with good initial settings that facilitate training in new environments.
Learning to Continually Learn
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it.
Embodiment dictates learnability in neural controllers
Catastrophic forgetting continues to severely restrict the learnability of controllers suitable for multiple task environments.
