Yannic Kilcher Videos (Audio Only)

177 Episodes

1. Symbolic Knowledge Distillation: from General Language Models to Commonsense Models (Explained)

   Published: 10/25/2021
2. I took a Swiss train and it was awesome! Train Seat Review - SBB InterCity 1 - Geneva to St. Gallen

   Published: 10/25/2021
3. [ML News] Microsoft trains 530B model | ConvMixer model fits into single tweet | DeepMind profitable

   Published: 10/21/2021
4. [ML News] DeepMind does Nowcasting | The Guardian's shady reporting | AI finishes Beethoven's 10th

   Published: 10/11/2021
5. Grokking: Generalization beyond Overfitting on small algorithmic datasets (Paper Explained)

   Published: 10/11/2021
6. How far can we scale up? Deep Learning's Diminishing Returns (Article Review)

   Published: 10/4/2021
7. [ML News] Plagiarism Case w/ Plot Twist | CLIP for video surveillance | OpenAI summarizes books

   Published: 9/30/2021
8. Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment (Paper Explained)

   Published: 9/30/2021
9. [ML News] New ImageNet SOTA | Uber's H3 hexagonal coordinate system | New text-image-pair dataset

   Published: 9/28/2021
10. Does GPT-3 lie? - Misinformation and fear-mongering around the TruthfulQA dataset

    Published: 9/24/2021
11. Topographic VAEs learn Equivariant Capsules (Machine Learning Research Paper Explained)

    Published: 9/21/2021
12. [ML News] Roomba Avoids Poop | Textless NLP | TikTok Algorithm Secrets | New Schmidhuber Blog

    Published: 9/16/2021
13. Celebrating 100k Subscribers! (w/ Channel Statistics)

    Published: 9/16/2021
14. [ML News] AI predicts race from X-Ray | Google kills HealthStreams | Boosting Search with MuZero

    Published: 9/13/2021
15. ∞-former: Infinite Memory Transformer (aka Infty-Former / Infinity-Former, Research Paper Explained)

    Published: 9/6/2021
16. [ML News] Blind Chess AI Competition | Graph NNs for traffic | AI gift suggestions

    Published: 9/5/2021
17. ALiBi - Train Short, Test Long: Attention with linear biases enables input length extrapolation

    Published: 9/5/2021
18. [ML News] Stanford HAI coins Foundation Models & High-profile case of plagiarism uncovered

    Published: 8/30/2021
19. Fastformer: Additive Attention Can Be All You Need (Machine Learning Research Paper Explained)

    Published: 8/27/2021
20. PonderNet: Learning to Ponder (Machine Learning Research Paper Explained)

    Published: 8/23/2021