Engineering a Less Artificial Intelligence with Andreas Tolias - #379
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Today we’re joined by Andreas Tolias, Professor of Neuroscience at Baylor College of Medicine and Principal Investigator of the Neuroscience-Inspired Networks for Artificial Intelligence organization. We caught up with Andreas to discuss his recent perspective piece, “Engineering a Less Artificial Intelligence,” which explores the shortcomings of state-of-the-art learning algorithms in comparison to the brain. The paper also offers several ideas about how neuroscience can lead the quest for better inductive biases by providing useful constraints on representations and network architecture. We discuss the promise of deep neural networks, the differences between inductive bias and model bias, the role of interpretability, and the exciting future of biological systems and deep learning. The complete show notes can be found at twimali.com/talk/379.
#14: Neocortex: Organizational and Functional Principles with Dr. Andreas Tolias
Max Planck Florida’s Neurotransmissions Podcast
The neocortex is a hallmark of mammalian brain evolution, and the underlying principles that define cortical circuits have captured the attention of neuroscientists for decades. In this episode, we sit down with Andreas Tolias from Baylor College of Medicine to discuss how his lab is unraveling both the cellular organization of the neocortex, as well as the information processing power of cortical circuits. We also welcome first time host, Michael Yetman, to the show!