Resultados
45 artículosOrdenar
1:47:38EN
Cognitive Revolution "How AI Changes Everything"· 4 jul 2026Pódcast19 Neurons Can Drive a Car. Liquid AI Wants Foundation Models on Every ChipPresenta: Nathan LabenzRamin Hasani traces liquid neural networks from a worm's 300-cell brain to a 600-megabyte model that will talk from inside a Mercedes, and explains why architecture search now beats architecture avengers.
2:59:44ENCognitive Revolution "How AI Changes Everything"· 3 jun 2026PódcastTwo Endangered Languages Broke Transformers. Nested Learning Gave Models a Sleep Button.Presenta: Nathan LabenzGoogle researcher Ali Behrouz tells Nathan Labenz how stacking update frequencies — not just layers — and an offline sleep phase could give language models genuine continual learning.
1:21:56EN
Unsupervised Learning: With Jacob Effron· 15 may 2026PódcastYann LeCun Left Meta Because LLMs Will Not Get You to IntelligencePresenta: Jacob EffronThe Turing Award winner tells Jacob Effron why he spun AMI Labs out of Meta, why JEPA-style world models beat pixel generators, and why he thinks Hinton changed his mind in 2023.
2:02:17ENCognitive Revolution "How AI Changes Everything"· 27 ago 2025PódcastSAEs Find the Nouns. Parameter Decomposition Looks for the VerbsPresenta: Nathan LabenzGoodfire's Lee Sharkey argues that sparse autoencoders recover a network's variables, not the algorithms those variables run, and shows how stochastic parameter decomposition tries to recover the computations themselves.
1:54:08ENCognitive Revolution "How AI Changes Everything"· 29 may 2025PódcastWhy Anthropic's first check went to a company building microscopes for neural netsPresenta: Nathan LabenzGoodfire's Dan Balsam and Tom McGrath argue that mechanistic interpretability now has a proto-paradigm, two stubborn gaps, and three products worth shipping today.
1:43:54ENCognitive Revolution "How AI Changes Everything"· 23 mar 2025PódcastA Year to Grow a Brain Organoid, an Hour to Simulate ItPresenta: Nathan LabenzStanford postdoc Siyu He tells Nathan Labenz how Squidiff and CORAL move single-cell and spatial experiments into the computer — and where the models still cannot go.
1:40:22ENCognitive Revolution "How AI Changes Everything"· 22 ene 2025PódcastTwenty-atom crystals taught an AI the physics of a heartbeatPresenta: Nathan LabenzOrbital Materials' Jonathan Godwin and Tim Duignan tell Nathan Labenz how a neural network trained on tiny crystals simulated a potassium ion channel on a single 2017 GPU.
1:42:16ENCognitive Revolution "How AI Changes Everything"· 4 jul 2024Pódcast267 Papers in Seven Months: Albert Gu Explains the State Space Model RevolutionPresenta: Nathan LabenzThe Mamba co-author walks through five years of recurrent-model work, why selective compression beats a growing KV cache, and what Mamba 2 trades away to train faster.
1:54:01ENCognitive Revolution "How AI Changes Everything"· 26 jun 2024PódcastA Tiny Network Grew a Salt Crystal the Training Data Never ShowedPresenta: Nathan LabenzTim Duignan trained tens of thousands of parameters on salt water. The model invented a crystal — and a continuum solvent theory he had spent a PhD failing to write by hand.
1:52:18ENCognitive Revolution "How AI Changes Everything"· 6 may 2024PódcastTwo Weeks, Thirty Compiles: How Adam Majmudar Wrote a GPU From ScratchPresenta: Nathan LabenzA Cognitive Revolution walkthrough of TinyGPU, from SIMD kernels and memory latency to an open-source chip flow that runs on a laptop.
1:19:24ENCognitive Revolution "How AI Changes Everything"· 5 abr 2024PódcastA Gibberish Prompt Unlocks What GPT-J Plans Three Tokens AheadPresenta: Nathan LabenzNortheastern’s Bau Lab shows that a 40,000-parameter soft prompt can read a model’s future words, and that about ten attention heads carry the task itself.
2:30:06ENCognitive Revolution "How AI Changes Everything"· 22 dic 2023PódcastTrained on a Thirtieth of GPT-4's Tokens, Mamba Beat Transformers on Home TurfPresenta: Nathan LabenzIn a solo emergency episode, Nathan Labenz argues that Albert Gu and Tri Dao's selective state space model is the first architecture since 2017 that deserves to share the Transformer’s throne.
1:40:07ENCognitive Revolution "How AI Changes Everything"· 4 jul 2023PódcastThirty thousand voltage updates a second: inside Skydio’s autonomy stackPresenta: Nathan LabenzHayk Martiros walks Nathan Labenz through a two-pound drone that sees in every direction, runs more than ten neural nets on board, and will not be weaponized.
1:52:46ENCognitive Revolution "How AI Changes Everything"· 27 jun 2023PódcastCharge Neural Nets by Connection Length, and the Black Box Splits Into Modules You Can SeePresenta: Nathan LabenzMIT physicist Ziming Liu walks Nathan Labenz through BIMT, a brain-inspired training trick that sparsifies networks until you can read them by looking.
1:21:20ENCognitive Revolution "How AI Changes Everything"· 9 mar 2023PódcastFreeze the eyes and the brain. Train only the optic nerve.Presenta: Nathan LabenzJunnan Li and Dongxu Li tell Nathan Labenz how BLIP cleaned noisy web captions, and how BLIP-2 connected a frozen vision model to a frozen language model in under ten days on one A100.
46:25EN
Lex Fridman· 17 ene 2019PódcastDeep Learning at the Edge of 2019: BERT, Autopilot, and the Ideas That Broke ThroughPresenta: Lex FridmanA tour of the architectural, applied, and automation breakthroughs that defined deep learning in 2018 and set up 2019.
1:29:03ENLex Fridman· 27 sept 2016PódcastFrom Word Vectors to Memory Networks: The Building Blocks of Deep NLPPresenta: Lex FridmanRichard Socher explains how word embeddings, recurrent models, GRUs, pointer mixtures, and dynamic memory networks turn language tasks into trainable end-to-end systems.
1:00:51ENLex FridmanPódcastDeep Learning From the Ground Up: Hugo Larochelle's One-Hour Tour of Neural Network FoundationsPresenta: Lex FridmanA fast, equation-level walk through feed-forward networks, backpropagation, practical training tricks, dropout and batch normalization, from the 2016 Deep Learning School.
1:07:29ENLex FridmanPódcastDeep Reinforcement Learning from First Principles: Rewards, Q-Learning, Policy Gradients and AlphaZeroPresenta: Lex FridmanLex Fridman's MIT 6.S091 opening lecture walks from the basic RL framework through DQN, actor-critic methods and AlphaZero to the unsolved problem of moving from simulation to the real world.
1:25:16ENLex FridmanPódcastFrom Hand-Built Features to ResNets: Andrej Karpathy's Crash Course in Convolutional NetworksPresenta: Lex FridmanA 2016 Deep Learning School talk covering how convnets work, how the ImageNet winners evolved, and how to apply them without being a hero.
1:24:43ENLex FridmanPódcastFrom Sparse Coding to GANs: A Tour of Unsupervised Deep Learning in 2016Presenta: Lex FridmanRuslan Salakhutdinov walks through autoencoders, Boltzmann machines, variational autoencoders and adversarial networks at the Deep Learning School, with candid notes on what did and did not work.
58:46ENLex FridmanPódcastCaging the Neural Network: How Aptiv Thinks About Safe Self-DrivingPresenta: Lex FridmanAptiv Autonomous Mobility's Karl Iagnemma and Oscar Beijbom explain why end-to-end learning is hard to trust in cars, and show how PointPillars and nuScenes push lidar perception forward.
1:15:59ENLex FridmanPódcastSteering Through Time: How Recurrent Networks and LSTMs Learn from SequencesPresenta: Lex FridmanLex Fridman's MIT 6.S094 lecture walks from backpropagation basics to LSTMs and the way they are used to predict steering in self-driving cars.
1:31:52ENLex FridmanPódcastFrom Phonemes to CTC: How Deep Learning Rebuilt Speech RecognitionPresenta: Lex FridmanBaidu's Adam Coates walks through the traditional speech pipeline, the CTC-based end-to-end engine that replaced much of it, and what it takes to scale and deploy it.Cargar másMostrando 24 de 45