Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible may not be initially available for training, and given incrementally. Deep learning models need to deal this two-fold problem in order perform well real-life situations. In paper, we propose a novel Few-Shot Lifelong Learning (FSLL) method that enables deep lifelong/continua...

In the pre-pandemic world learning was most often onsite, in-person and co-located. This turned upside down during pandemic where online suddenly became ‘new normal’. To continue in a world, providers institutions were required to rethink reconfigure more ‘pandemic-friendly’ formats. aftermath of emergency teaching learning, providers, developers teachers are now looking ahead contemplate its i...

We consider the problem of knowledge transfer when an agent is facing a series Reinforcement Learning (RL) tasks. introduce novel metric between Markov Decision Processes and establish that close MDPs have optimal value functions. Formally, functions are Lipschitz continuous with respect to tasks space. These theoretical results lead us value-transfer method for Lifelong RL, which we use build ...