October 2021 - Artificial Intelligence Videos

Order By: Views

47:49

PyTorch Community Voices | PyTorchTS & Fashion-MNIST | Kashif Rasul

Join us for an interview with star PyTorch community member Kashif Rasul as we learn about and discuss PyTorchTS, a PyTorch Probabilistic Time Series forecasting framework which provides state of the art PyTorch time series models by utilizing GluonTS as its back-end API and for loading, transforming and back-testing time series data sets. Kashif is […]

01:02:50

Neural Compression — Lecture 1 — Problem Setting & Symbol Codes

First full lecture of the course “Data Compression With Deep Probabilistic Models” by Prof. Robert Bamler at University of Tübingen (summer term of 2021). These videos were deliberately recorded at a calm pace. Click the cogwheel in the lower right corner of the video player to adjust playback speed to your personal preference. Playlist for […]

40:47

Unbiased Learning from Biased User Feedback with Thorsten Joachims – TWiML Talk #207

In the final episode of our re:Invent series, we’re joined by Thorsten Joachims, Professor in the Department of Computer Science at Cornell University. Thorsten participated at the conference’s AI Summit, presenting his research on “Unbiased Learning from Biased User Feedback.” In our conversation, we take a look at some of the inherent and introduced biases […]

00:56

Announcing PyTorch Hackathon 2021 — Sept 8 – Nov 3, 2021

We’re excited to announce the PyTorch Annual Hackathon 2021! This year, we’re looking to support the community in creating innovative PyTorch tools, libraries, and applications. 2021 is the third year we’re hosting this Hackathon, and we welcome you to join the PyTorch community and put your machine learning skills into action. Submissions start on September […]

44:15

Computer Vision – Lecture 4.1 (Stereo Reconstruction: Preliminaries)

Lecture: Computer Vision (Prof. Andreas Geiger, University of Tübingen)

29:21

Tuomas Sandholm Interview – Solving Imperfect-Information Games – NIPS ’17 Best Paper

In this episode I speak with Tuomas Sandholm, Carnegie Mellon University Professor and Founder and CEO of startups Optimized Markets and Strategic Machine. Tuomas, along with his PhD student Noam Brown, won a 2017 NIPS Best Paper award for their paper “Safe and Nested Subgame Solving for Imperfect-Information Games.” Tuomas and I dig into the […]

283

10:35

Applied AI at The Coca-Cola Company (TensorFlow Dev Summit 2018)

In 2016, Coca-Cola updated its core loyalty marketing program to a mobile-first web platform. The program requires consumers to input 14-character proof-of-purchase codes for entry into promotions. Consumer engagement would have been badly impacted if users had been required to thumb-enter these codes into web forms on their mobile devices. To solve this problem, Coca-Cola […]

41:22

Deep Learning – Lecture 8.3 (Sequence Models: Gated Recurrent Networks)

Lecture: Deep Learning (Prof. Andreas Geiger, University of Tübingen)

43:32

Disentangled Representations & Google Research Football with Olivier Bachem – TWIML Talk #293

Today we’re joined by Olivier Bachem, a research scientist at Google AI on the Brain team. Initially, Olivier joined us to discuss his work on Google’s research football project, their foray into building a novel reinforcement learning environment, but we spent a fair amount of time exploring his research in disentangled representations. Olivier and Sam […]

00:10

De Fauw et al. Nature Medicine (2018): Supplementary Video 4: DME

Supplementary Video 4 from the article De Fauw et al. “Clinically applicable deep learning for diagnosis and referral in retinal disease”. Nature Medicine (in press) (2018), DOI: 10.1038/s41591-018-0107-6 Accumulation of this fluid in the macula – diabetic macular edema (DME) – is the commonest cause of visual impairment in diabetes. A 54-year old man with […]

107

12:28

Building a Deep Learning Image Classifier | Learning Intelligence 43

Josh and I have been thinking about using CoreML on the iPhone to harness the power of an image classifier machine learning model for recognising food. So we decided to practice with banana not banana. LINKS FROM THE SHOW: Deep Learning Image Classifier Guide – https://www.pyimagesearch.com/2017/12/11/image-classification-with-keras-and-deep-learning/ CONNECT: Web – http://bit.ly/mrdbourkeweb Quora – http://bit.ly/mrdbourkequora Medium – […]

185

00:58

AI Learns To Play Snake In 100 Games #Shorts

Watch how an AI Learns To Play Snake in 100 Games. The algorithm is implemented in Python with Pygame and PyTorch. ⭐ Join Our Discord : https://discord.gg/FHMg9tKFSN 🚀🚀 Get monthly Python and ML Tips: https://www.python-engineer.com/newsletter/ 🚀🚀 SUPPORT ME ON PATREON: https://www.patreon.com/patrickloeber If you enjoyed this video, please subscribe to the channel! Snake AI Tutorial: https://youtu.be/PJl4iabBEz0 […]

09:40

Disney's Creative Genome by Miquel Farré | PyTorch Ecosystem Day 2021

Miquel Farré is a senior technology manager at Disney, taking the lead on projects at the intersection of video technology, machine learning and web applications. Metadata that drives content searchability is most often indexed at the title level, with limited governance and high ambiguity; at best, keyword metadata has been added to a title as […]

240

07:20

Vision par Ordinateur à l’aide de l’Apprentissage Automatique (Coding TensorFlow en français)

This video is available in English: https://goo.gle/2Od8kvx Dans le deuxième épisode de l’Apprentissage Automatique : Zero to Hero, l’avocat d’Amnesty International Laurence Moroney (lmoroney @) nous montre la vision par ordinateur à l’aide de l’apprentissage automatique. Un exemple de vision par ordinateur, au-delà de Hello World : https://goo.gle/34cHkDk Voir plus de code TensorFlow → https://goo.gle/2Y43cN4 […]

41:39

GenZ: The brands GenZ wants to buy

GenZ: The brands GenZ wants to buy GenZ is the most eco-conscious and socially-aware generation yet. They want brands that walk the talk and put people and the environment first. So how can brands drive positive change and win the loyalty of younger generations? This session dives into the growing movement towards conscious capitalism and […]

39:25

Global Leadership: What does it take to be a responsible leader of AI?

Global Leadership: What does it take to be a responsible leader of AI? Business leaders looking to leverage the power of data and AI find themselves navigating evolving regulations and a sea of new ethical, governance and organisational considerations. So what does the journey toward responsible AI actually look like for companies committed to best […]

12:18

PyTorch Partner Collaborations by Geeta Chauhan | PyTorch Ecosystem Day 2021

Geeta Chauhan leads AI Partnership Engineering at Facebook AI with expertise in building resilient, anti-fragile, large scale distributed platforms for startups and Fortune 500s. As a core member of the PyTorch team, she leads TorchServe and many partner collaborations for building a strong PyTorch ecosystem and community. Learn more about how PyTorch integrates with partners […]

19:40

We Finished Spartan ULTRA 2018

On April 28, 2018, our legs took us further than they ever have in one day. Chris, Zeno and I ran the Spartan Ultra. A 50km+, 60+ obstacle race in Brisbane Australia. AROOOOOO! OTHER EPISODES: 1. Beginning of the preparation: https://youtu.be/0YUxK6g3U2M 2. Spartan training getting me jacked: https://youtu.be/v3UbklZAdbQ 3. Training and eating 2-weeks out: https://youtu.be/GYzXJgS_p-4 […]

22:18

(A) Linear algebra 6: Invertible maps and matrices

Part of the Course “Mathematics for Machine Learning”, Winter Term 2020/21, Ulrike von Luxburg, University of Tübingen Source of this “Tübingen Machine Learning” AI Video

08:01

UAI 2021: Learnable Uncertainty under Laplace Approximations

——————————————————————————– Learnable Uncertainty under Laplace Approximations Agustinus Kristiadi, Matthias Hein, and Philipp Hennig Uncertainty in Artificial Intelligence (UAI) 2021 ——————————————————————————– ► Paper: https://arxiv.org/abs/2010.02720 ► Code: https://github.com/wiseodd/lula Laplace approximations are classic, computationally lightweight means for constructing Bayesian neural networks (BNNs). As in other approximate BNNs, one cannot necessarily expect the induced predictive uncertainty to be calibrated. […]

51:56