Introducing Command R+: Our new, most powerful model in the Command R family.

Learn More

Cohere For AI - Guest Speaker:Hasan Abed Al Kader Hammoud, PhD Student

other

Date: May 13, 2024

Time: 4:00 PM - 5:00 PM

Location: Online

Short Bio: Hasan is a PhD student at King Abdullah Univesity of Science and Technology (KAUST) under the supervision of Bernard Ghanem. Hasan has worked in multi topics such as robustness, 3D understanding, LLM agents, and continual learning. The work to be presented in this session is on data diversity and self-supervised training which was completed during Hasan's internship at The University of Oxford.

Abstract: We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed computational budget. Our findings consistently demonstrate that increasing pretraining data diversity enhances SSL performance, albeit only when the distribution distance to the downstream data is minimal. Notably, even with an exceptionally large pretraining data diversity achieved through methods like web crawling or diffusion-generated data, among other ways, the distribution shift remains a challenge. Our experiments are comprehensive with seven SSL methods using large-scale datasets such as ImageNet and YFCC100M amounting to over 200 GPU days. Code and trained models will be available at https://github.com/hammoudhasan/DiversitySSL

Add event to calendar

Apple Google Office 365 Outlook Outlook.com Yahoo