In this second part of our conversation, (listen to the first part) David and I discuss his thoughts about current language and speech techniques in AI, his thoughts about the prospects of artificial general intelligence, the challenge of mapping the parts of linguistics onto the parts of neuroscience, the state of graduate training, and more.

• Visit David's lab website at NYU.
• He’s also a director at Max Planck Institute for Empirical Aesthetics.
• Follow him on twitter: @davidpoeppel.
• Some of the papers we discuss or mention (lots more on his website):
  • The cortical organization of speech processing.
  • The maps problem and the mapping problem: Two challenges for a cognitive neuroscience of speech and language.
• A good talk:
  • What Language Processing in the Brain Tells Us About the Structure of the Mind.
• Transformer model:
• How do Transformers Work in NLP? A Guide to the Latest State-of-the-Art Models.
• Attention Is All You Need.

Support the Podcast

David and I talk about his work to understand how sound waves floating in the air get transformed into meaningful concepts in your mind. He studies speech processing and production, language, music, and everything in between, approaching his work with steadfast principles to help frame what it means to understand something scientifically. We discuss many of the hurdles to understanding how our brains work and making real progress in science, plus a ton more.

• Visit David's lab website at NYU.
• He’s also a director at Max Planck Institute for Empirical Aesthetics.
• Follow him on twitter: @davidpoeppel.
• For a related episode (philosophically), you might re-visit my discussion with John Krakauer.
• Some of the papers we discuss or mention (lots more on his website):
  • The cortical organization of speech processing.
  • The maps problem and the mapping problem: Two challenges for a cognitive neuroscience of speech and language.
• A good talk:
  • What Language Processing in the Brain Tells Us About the Structure of the Mind.
• NLP Transformer model:
  • How do Transformers Work in NLP? A Guide to the Latest State-of-the-Art Models.
  • Attention Is All You Need.

Support the Podcast

Show notes:

Raia and I discuss her work at DeepMind figuring out how to build robots using deep reinforcement learning to do things like navigate cities and generalize intelligent behaviors across different tasks. We also talk about challenges specific for embodied AI (robots), how much of it takes inspiration from neuroscience, and lots more.

• Raia’s website.
• Follow her on Twitter: @RaiaHadsell
• Papers relevant to our discussion:
  • Learning to Navigate in Cities without a Map.
  • Overcoming catastrophic forgetting in neural networks.
  • Progressive neural networks.
• A few Talks:
  • Deep reinforcement learning in complex environments.
  • Progressive Nets & Transfer.
• The new Neuro-AI conference she's starting with Tony Zador and Blake Richards:
  • From Neuroscience to Artificially Intelligent Systems (NAISys) 

Talia and I discuss her work on how our visual system is organized topographically, and divides into three main categories: big inanimate things, small inanimate things, and animals. Her work is unique in that it focuses not on the classic hierarchical processing of vision (though she does that, too), but what kinds of things are represented along that hierarchy. She also uses deep networks to learn more about the visual system. We also talk about her keynote talk at the Cognitive Computational Neuroscience conference and plenty more.

Show notes:

• Talia’s lab website.
• Follow her on twitter: @talia_konkle.
• Check out the Cognitive Computational Neuroscience conference, where she'll give a keynote address.
• Papers we discuss/reference:
  • Early work on the tripartite organization. Tripartite Organization of the Ventral Stream by Animacy and Object Size.
  • A more recent update, with the texforms we discuss and comparision too deep learning CNN networks used to model the ventral visual stream. Mid-level visual features underlie the high-level categorical organization of the ventral stream.
• The article Talia references about an elegant solution to an old problem in computer science.

How does knowledge in the world get into our brains and integrated with the rest of our knowledge and memories? Anna and I talk about the complementary learning systems theory introduced in 1995 that posits a fast episodic hippopcampal learning system and a slower statistical cortical learning system. We then discuss her work that advances and adds missing pieces to the CLS framework, and explores how sleep and sleep cycles contribute to the process. We also discuss how her work might contribute to AI systems by using multiple types of memory buffers, a little about being a woman in science, and how it’s going with her brand new lab.

• Anna’s Penn Computational Cognitive Neuroscience Lab.
• Follow Anna on Twitter: @annaschapiro.
• Papers we discuss:
  • The original Complimentary Learning Systems paper: 
    • Complimentary Learning Systems Theory and Its Recent Update.
  • Anna’s work on CLS and Hippocampus:
    • The hippocampus is necessary for the consolidation of a task that does not require the hippocampus for initial learning.
    • Complementary learning systems within the hippocampus: a neural network modelling approach to reconciling episodic memory with statistical learning.
  • Examples of her work on sleep:
    • Active and effective replay: Systems consolidation reconsidered again.
    • Switching between internal and external modes: A multiscale learning principle.
    • Sleep Benefts Memory for Semantic Category Structure While Preserving Exemplar-Specifc Information.

This is part 2 of my conversation with Brad (listen to part 1 here). We discuss how Moore’s law is on its last legs, and his ideas for how neuroscience - in particular neural algorithms - may help computing continue to scale in a post-Moore’s law world. We also discuss neuromporphics in general, and more.

• Brad's homepage.
• Follow Brad on Twitter: @jbimaknee.
• The paper we discuss:
  • Neural Algorithms and Computing Beyond Moore's Law.
• Check out the Neuro Inspired Computing Elements (NICE) workshop - lots of great talks and panel discussions.

In this first part of our discussion, Brad and I discuss the state of neuromorphics and its relation to neuroscience and artificial intelligence.  He describes his work adding new neurons to deep learning networks during training, called neurogenesis deep learning, inspired by how neurogenesis in the dentate gyrus of the hippocampus helps learn new things while keeping previous memories intact. We also talk about his method to transform deep learning networks into spiking neural networks so they can run on neuromorphic hardware, and the neuromorphics workshop he puts on every year, the Neuro Inspired Computational Elements (NICE) workshop.

Show Notes:

• Brad's homepage.
• Follow Brad on Twitter: @jbimaknee.
• The papers we discuss:
  • Computational Influence of Adult Neurogenesis on Memory Encoding.
  • Neurogenesis Deep Learning.
  • Training deep neural networks for binary communication with the Whetstone method.
    • And here's the arXiv version.
• Check out the Neuro Inspired Computing Elements (NICE) workshop - lots of great talks and panel discussions.

Show Notes:

• Nando’s CIFAR page.
• Follow Nando on Twitter: @NandoDF
• He's giving a keynote address at Cognitive Computational Neuroscience Meeting 2020.
• Check out his famous machine learning lectures on Youtube.
• Papers we (more allude to than) discuss:
  • Neural Programmer-Interpreters.
  • Learning to learn by gradient descent by gradient descent.
  • Dueling Network Architectures for Deep Reinforcement Learning.
  • Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions.
  • One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL.

Show notes:

• Check out Anne's lab website.
• Follow her on twitter: @anne_churchland
• Anne's List, the list of female systems neuroscientists to invite as speakers.
• The papers we discuss:
  • Single-trial neural dynamics are dominated by richly varied movements.
  • Lapses in perceptual judgments reflect exploration.
  • Complexity vs Stimulus-Response Compatibility vs Stimulus-response ethological validity.
  • Perceptual Decision-Making: A Field in the Midst of a Transformation.

Show notes:

• Máté's Cambridge website.
• He's part of the Computational Learning and Memory Group there.
• Here's his webpage at Central European University.
• A review to introduce his subsequent work:
  • Statistically optimal perception and learning: from behavior to neural representations.
• Related recent talks:
  • Bayesian models of perception, cognition and learning - CCCN 2017.
  • Sampling: coding, dynamics, and computation in the cortex (Cosyne 2018).