Drawing inspiration from human learning behaviors, this work proposes a novel approach to mitigate catastrophic forgetting in Prompt-based Continual Learning models by exploiting the relationships between continuously emerging class data. We find that applying human habits of organizing and connecting information can serve as an efficient strategy when training deep learning models. Specifically, by building a hierarchical tree structure based on the expanding set of labels, we gain fresh insights into the data, identifying groups of similar classes could easily cause confusion. Additionally, we delve deeper into the hidden connections between classes by exploring the original pretrained model's behavior through an optimal transport-based approach. From these insights, we propose a novel regularization loss function that encourages models to focus more on challenging knowledge areas, thereby enhancing overall performance. Experimentally, our method demonstrated significant superiority over the most robust state-of-the-art models on various benchmarks.

Located in Santa Monica, CA. Are you looking for an applied data science internship? Develop machine learning, NLP, and statistical solutions for real users–image processing, text generation, and more. Our goal is for you to become a self-sufficient team member. We will give you pragmatic practice of your technical skills.

Cryptocurrencies have come a long way since Bitcoin was first announced in late 2008. In just a decade the market has skyrocketed from zero to an estimated $400bn, and a further 3,000 cryptocurrencies have since launched. But this success has not been without its ups and downs. Bitcoin alone has fluctuated from almost $20,000 to less than a cent during this time. There's a lot of money to be made in cryptocurrency, and a lot of money to be lost.