1635021487_maxresdefault.jpg
0
26:17

(5/5) AlphaVertex – Creating a Worldwide Financial Knowledge Graph

This week I’m on location at NYU/ffVC AI NexusLab startup accelerator, speaking with founders from the 5 companies in the program’s inaugural batch. This interview is with AlphaVertex, a FinTech startup creating a worldwide financial knowledge graph to help investors predict stock prices. The notes for this series can be found at twimlai.com/nexuslab. Thanks to […]
1640365035_maxresdefault.jpg
197
31:15

[ML News] AI learns to search the Internet | Drawings come to life | New ML journal launches

#webgpt #aiart #mlnews The latest and greatest from the Machine Learning world. OUTLINE: 0:00 – Intro 0:20 – Sponsor: Weights & Biases 2:40 – WebGPT: When GPT-3 can search the Internet 15:45 – MetaAI brings children’s drawings to life 17:15 – OpenAI lets anyone fine-tune GPT-3 18:15 – New Journal: Transactions on Machine Learning Research […]
1633043166_maxresdefault.jpg
214
21:17

[News] Facebook’s Real-Time TTS system runs on CPUs only!

Facebook AI’s new Text-To-Speech system is able to create 1 second of speech in as little as 500ms, making it real-time. What’s even more impressive is the fact that this does not require a rack of GPUs, but runs on merely 4 CPUs. OUTLINE: 0:00 – Intro 1:00 – Problem Formulation 3:20 – System Explanation […]
1629390502_maxresdefault.jpg
88
02:56:04

#035 Christmas Community Edition!

Welcome to the Christmas special community edition of MLST! We discuss some recent and interesting papers from Pedro Domingos (are NNs kernel machines?), Deepmind (can NNs out-reason symbolic machines?), Anna Rodgers – When BERT Plays The Lottery, All Tickets Are Winning, Prof. Mark Bishop (even causal methods won’t deliver understanding), We also cover our favourite […]
1629356813_maxresdefault.jpg
105
52:26

#044 – Data-efficient Image Transformers (Hugo Touvron)

Today we are going to talk about the Data-efficient image Transformers paper or (DeiT) which Hugo is the primary author of. One of the recipes of success for vision models since the DL revolution began has been the availability of large training sets. CNNs have been optimized for almost a decade now, including through extensive […]
1629255426_maxresdefault.jpg
407
01:36:22

#55 Self-Supervised Vision Models (Dr. Ishan Misra – FAIR).

Dr. Ishan Misra is a Research Scientist at Facebook AI Research where he works on Computer Vision and Machine Learning. His main research interest is reducing the need for human supervision, and indeed, human knowledge in visual learning systems. He finished his PhD at the Robotics Institute at Carnegie Mellon. He has done stints at […]
1634691619_maxresdefault.jpg
10
59:53

#TWIMLfest: Accessibility and Computer Vision

Digital imagery is pervasive today. More than a billion images per day are produced and uploaded to social media sites, with many more embedded within websites, apps, digital documents, and eBooks. Engaging with digital imagery has become fundamental to participating in contemporary society, including education, the professions, e-commerce, civics, entertainment, and social interactions. However, most […]
1634574919_maxresdefault.jpg
30
49:06

#TWIMLfest: Deep Learning for Time Series in Industry

A survey of the promise and barriers to leveraging deep time series models. In this session we will go over some of the latest research on using LSTMs, other RNNs, and transformer models to forecast multivariate time series data and dive into how they compare to more classical methods. This session aims to present attendees […]
1634459276_maxresdefault.jpg
41
01:14:48

#TWIMLfest: Live Keynote Interview with Jeremy Howard – #421

Join Sam and friend of the show Jeremy Howard, creator of the popular fast.ai coursework, for a Keynote Interview! Sam and Jeremy explore topics such as the importance of building a strong community as a foundation, the current landscape and future of AI education, and of course, the recently released fast.ai course: Practical Deep Learning […]
1634627512_maxresdefault.jpg
22
01:03:13

#TWIMLfest: Live Keynote Interview with Shakir Mohamed – #418

In this special #TWIMLfest edition of the podcast, we’re joined by Shakir Mohamed, a Senior Research Scientist at DeepMind. Shakir is also a leader of Deep Learning Indaba, a non-profit organization whose mission is to Strengthen African Machine Learning and Artificial Intelligence. In our conversation with Shakir, we discuss his recent paper ‘Decolonial AI,’ the […]
1634854789_maxresdefault.jpg
16
01:03:06

#TWIMLfest: Live Keynote Interview with Suzana Ilić

In this special #TWIMLfest episode, we’re joined by Suzana Ilić, a computational linguist at Causaly and founder of Machine Learning Tokyo (MLT). Suzana joined us as a keynote speaker to discuss the origins of the MLT community, but we cover a lot of ground in this conversation. We briefly discuss Suzana’s work at Causaly, touching […]
1634999403_maxresdefault.jpg
15
01:27:36

#TWIMLfest: Office Hours – Natural Language Processing

In the Office Hours series, we invite experts and practitioners in various topic areas for AMA (ask-me-anything) style sessions to answer community member questions. The intent is to answer technical questions and/or help participants advance their specific projects and interests. This week’s topic will be centered on NLP! For more sessions like this, visit https://twimlfest.com! […]
1636328480_hqdefault.jpg
1.54K
03:58

10 More Cool Deep Learning Applications | Two Minute Papers #52

In this episode, we present another round of incredible deep learning applications! _________________________ 1. Colorization – http://tinyclouds.org/colorize/ 2. RNN Music on Bob Sturm’s YouTube channel – https://www.youtube.com/watch?v=RaO4HpM07hE 3. Flow Machines by Sony – https://www.youtube.com/watch?v=buXqNqBFd6E 4. RNN Passwords – https://github.com/gehaxelt/RNN-Passwords 5. Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding – http://arxiv.org/abs/1510.00149 […]
1634703417_maxresdefault.jpg
13
01:03:51

2020: A Critical Inflection Point for Responsible AI with Rumman Chowdhury

Today we’re joined by Rumman Chowdhury, Managing Director and Global Lead of Responsible Artificial Intelligence at Accenture. In our conversation with Rumman, we explored questions like: • Why is now such a critical inflection point in the application of responsible AI? • How should engineers and practitioners think about AI ethics and responsible AI? • […]
1635261446_maxresdefault.jpg
6
07:44

3 Benefits of Cold Showers

I’ve been taking cold showers for the past few months. At the start they sucked and they still suck but the feeling I get after taking one is well and truly worth it. There are hundreds of benefits to cold showers and in today’s episode, I go over my top three. Thank you all for […]
1634925060_maxresdefault.jpg
16
18:34

3 Life Principles I Learned From Ray Dalio

Ray Dalio is the founder of Bridgewater Associates, one of the largest hedge funds in the world. His net worth is somewhere around $16 Billion. I recently finished reading his book Principles: Life and Work and it left an impact on me. My copy is loaded with highlights. In this episode, I share three of […]
1634363226_hqdefault.jpg
15
36:47

3D Deep Learning with PyTorch 3D w/ Georgia Gkioxari – #408

Today we’re joined by Georgia Gkioxari, a research scientist at Facebook AI Research. Georgia was hand-picked by the TWIML community to discuss her work on the recently released open-source library PyTorch3D. In our conversation, Georgia describes her experiences as a computer vision researcher prior to the 2012 deep learning explosion, and how the entire landscape […]
1634481571_hqdefault.jpg
22
39:17

3D Deep Learning with PyTorch 3D w/ Georgia Gkioxari – #408

In this episode, we’re joined by Georgia Gkioxari, a research scientist at Facebook AI Research. Georgia was hand-picked by the TWIML community to discuss her work on the recently released open-source library PyTorch3D. In our conversation, Georgia describes her experiences as a computer vision researcher prior to the 2012 deep learning explosion, and how the […]
1634312623_maxresdefault.jpg
356
14:34

3D Deep Learning with PyTorch3D

Facebook AI Research Engineer Nikhila Ravi presents an informative overview of PyTorch3D, a library of optimized, efficient, reusable components in PyTorch for state-of-the-art 3D deep learning tasks. Efficiency, modularity, and differentiability are the key elements of PyTorch3D that bring faster performance to any 3D Deep Learning project. Subscribe to this page to get the latest […]
1634328479_maxresdefault.jpg
351
28:49

3D Deep Learning with PyTorch3D by Nikhila Ravi

Facebook AI Research Engineer Nikhila Ravi presents an informative overview of PyTorch3D, a library of optimized, efficient, reusable components in PyTorch for state-of-the-art 3D deep learning tasks. Efficiency, modularity, and differentiability are the key elements of PyTorch3D that bring faster performance to any 3D Deep Learning project. Source of this PyTorch AI Video
1634578286_maxresdefault.jpg
45
08:00

5 Handstand Progression Exercises You Should Be Doing

If you’re like me, your lack of upper body mobility and stability holds you back from being able to hold a handstand for longer than a couple of seconds. These are some of the exercises I’ve been practising lately to improve my handstand. Sometimes to do the cool movements, you have to start with and […]