About this Episode

This week, we continue our conversations around the topic of Data-Centric AI joined by a friend of the show Adrien Gaidon, the head of ML research at the Toyota Research Institute (TRI). In our chat, Adrien expresses a fourth, somewhat contrarian, viewpoint to the three prominent schools of thought that organizations tend to fall into, as well as a great story about how the breakthrough came via an unlikely source. We explore his principle-centric approach to machine learning as well as the role of self-supervised machine learning and synthetic data in this and other research threads. Make sure you’re following along with the entire DCAI series at twimlai.com/go/dcai.

To learn more about this episode, or to access the full resource list, visit twimlai.com/go/575

Originally published at https://twimlai.com on May 23, 2022.

--

--

About this Episode

Today we’re joined by Auke Wiggers, an AI research scientist at Qualcomm. In our conversation with Auke, we discuss his team’s recent research on data compression using generative models. We discuss the relationship between historical compression research and the current trend of neural compression, and the benefit of neural codecs, which learn to compress data from examples. We also explore the performance evaluation process and the recent developments that show that these models can operate in real-time on a mobile device. Finally, we discuss another ICLR paper, “Transformer-based transform coding”, that proposes a vision transformer-based architecture for image and video coding, and some of his team’s other accepted works at the conference.

To learn more about this episode, or to access the full resource list, visit twimlai.com/go/570

Originally published at https://medium.com on May 03, 2022.

--

--

About this Episode

Today we’re joined by Irwan Bello, formerly a research scientist at Google Brain, and now on the founding team at a stealth AI startup. We begin our conversation with an exploration of Irwan’s recent paper, Designing Effective Sparse Expert Models, which acts as a design guide for building sparse large language model architectures. We discuss mixture of experts as a technique, the scalability of this method, and it’s applicability beyond NLP tasks the data sets this experiment was benchmarked against. We also explore Irwan’s interest in the research areas of alignment and retrieval, talking through interesting lines of work for each area including instruction tuning and direct alignment.

To learn more about this episode, or to access the full resource list, visit twimlai.com/go/569

Originally published at https://medium.com on April 26, 2022.

--

--

The TWIML AI Podcast

The TWIML AI Podcast

The TWIML AI Podcast brings the top minds and ideas from the world of ML and AI to a broad and influential community of ML/AI researchers, data scientists, etc.