Brain Inspired
Summary: Neuroscience and artificial intelligence work better together. Brain inspired is a celebration and exploration of the ideas driving our progress to understand intelligence. I interview experts about their work at the interface of neuroscience, artificial intelligence, cognitive science, philosophy, psychology, and more: the symbiosis of these overlapping fields, how they inform each other, where they differ, what the past brought us, and what the future brings. Topics include computational neuroscience, supervised machine learning, unsupervised learning, reinforcement learning, deep learning, convolutional and recurrent neural networks, decision-making science, AI agents, backpropagation, credit assignment, neuroengineering, neuromorphics, emergence, philosophy of mind, consciousness, general AI, spiking neural networks, data science, and a lot more. The podcast is not produced for a general audience. Instead, it aims to educate, challenge, inspire, and hopefully entertain those interested in learning more about neuroscience and AI.
- Visit Website
- RSS
- Artist: Paul Middlebrooks
- Copyright: © 2019 Brain-Inspired
Podcasts:
Cortical.ioThe white paper we discuss: Semantic Folding Theory And its Application in Semantic Fingerprinting. A nice talk Francisco gave: Semantic fingerprinting: Democratising natural language processing Francisco was influenced by Jeff Hawkins’ work and book On Intelligence. See episode 017 to learn more about Jeff Hawkins’ approach to modeling cortex. Douglas Hofstadter’s Analogy as the Core of Cognition.
Jay's homepage at Stanford.Implementing mathematical reasoning in machines:The video lecture.The paper.Parallel Distributed Processing by Rumelhart and McClelland.Complimentary Learning Systems Theory and Its Recent Update.Episode 28 with Sam Gershman about building machines that learn and think like humans.Check out my interview on Ginger Campbell's Brain Science podcast.
Show notes: Paul Humphreys' website.Zac Irving's website.Emergence: Emergence: A Philosophical Account. (book by Paul)The Oxford Handbook of Philosophy of Science. Mind Wandering: Mind-Wandering is Unguided Attention.The Philosophy of Mind-Wandering.The Neuroscience of Spontaneous Thought.
Show notes: Sam's Computational Cognitive Neuroscience Lab.Follow Sam on Twitter: @gershbrain.The papers we discuss: What does the free energy principle tell us about the brain?Building machines that learn and think like people. A video summarizing that work. The book Sam recommended: What Is Thought by Eric Baum.
Show notes: Websites: Ioana Marinescu, Konrad KordingTwitter: Twitter: @mioana; @KordingLabThe paper we discuss: Quasi-experimental causality in neuroscience and behavioral research.A Pre-print version. Judea Pearl's The Book of Why.Judea Pearl's online lecture about causality: The Art and Science of Cause and Effect.Ioana's review of Universal Basic Income: No Strings Attached.The post on hedge drift by Stefan Schubert: Hedge drift and advanced motte-and-bailey.Books recommended by Ioana and Konrad to understand causality: Mostly Harmless Econometrics.Mastering 'Metrics: The Path from Cause to Effect.
Image courtesy of Kendrick Kay: Brain art Show notes: Check out Kendrick’s lab website: CVN lab. Follow him on twitter: @cvnlab. The papers we discuss: Bottom-up and top-down computations in word- and face-selective cortex. Principles for models of neural information processing. Appreciating diversity of goals in computational neuroscience. A nice talk about the model we discuss: Bottom Up and Top Down Computations in Word- and Face-Selective Cortex Cognitive Computational Neuroscience conference.
Show notes BLAM (Brain, Learning, Animation, and Movement) Lab homepage: http://blam-lab.org/ BLAM on Twitter: @blamlab Papers we discuss: Neuroscience Needs Behavior: Correcting a Reductionist Bias. John and his brother David's interview in Current Biology: John and David Krakauer Mark Humphries’ piece on John’s “Neuroscience Needs Behavior” paper. Tinbergen’s 4 Questions. John’s book on stroke recovery: Broken Movement: The Neurobiology of Motor Recovery after Stroke (The MIT Press). David Marr’s classic work, Vision. More is Different by Phillip Anderson, and the hierarchical nature of scientific disciplines. Understanding Scientific Understanding by Henk W. De Regt. Inventing Temperature: Measurement and Scientific Progress by Hasock Chang. Soul Dust: The Magic of Consciousness by Nicholas Humphrey. The Organisation of Mind by Tim Shallice and Richard Cooper.
Show notes: Tim’s Neuroscience homepage: Follow Tim on Twitter: @behrenstim. Edward Tolman’s cognitive maps work: Cognitive maps in rats and men. Place Cells and Grid Cells: O’Keefe early place cell paper: The Hippocampus as a Spatial Map. O’Keefe’s book about the work: The Hippocampus as a Cognitive Map. Mosers and their students discover grid cells: Microstructure of a spatial map in the entorhinal cortex. Overview. Here’s a good talk Tim gives on the subject: Building models of the world for behavioural control. Tim's papers we discuss: What is a cognitive map? (Neuron, 2018) Organizing conceptual knowledge in humans with a grid-like code (Science, 2016) Two of the books he recommended: Theoretical Neuroscience by Dayan and Abbott. Information Theory, Inference and Learning Algorithms by David MacKay.
Marcel and I discuss his recent work using generative adversarial networks to decode brain activity to reconstruct images people saw, his work to restore vision to blind humans by stimulating early visual cortex, general AI, and even -- shutter -- consciousness a bit.
Melanie and I talk about the limitations of artificial intelligence in its current deep learning state (a la her New York Times Op-Ed), what AI needs to proceed toward general AI, what complexity is and how it relates to the fields of AI and neuroscience, and plenty more.
Matt and I discuss his neuroscience and AI research at DeepMind, including how AI benefits from neuroscience, his work on meta-reinforcement learning to create systems that learn more efficiently, how meta-reinforcement learning might be implemented in a neural circuit involving the prefrontal cortex and the dopamine system, how theory of mind might be implemented in machines to help them understand each other and to help us understand them, and a lot more.
Anna and I discuss home and DIY use of neurotechnology- specifically transcranial direct current stimulation (tDCS) and electroencephalography (EEG) products marketed to improve cognition. We talk about who uses these products and for what (enhancement or self-treatment), how they get marketed, and the possibilities for how they may get regulated.
Julie and I discuss her work using spintronic nano-devices to implement bio-inspired computing and neural networks in hardware. We talk about neuromorphic chips in general, their history, how they could solve the energy efficiency problem, where it’s all headed, some of the physics behind her nano-oscillators, and more.
Dean and I talk about how time and duration is encoded in the brain, how he implemented timing and sequences using short-term synaptic plasticity, in neuronal cultures, and in recurrent neural networks. We also discuss the subjective nature of time, consciousness, and how time might be implemented in future general AI.
Jeff and I discuss his new framework to understand how our cortex functions by building models of complete objects in all the cortical columns throughout the cortex. We also talk about his book On Intelligence, and I get his take on a number of other topics.
