1635192888_maxresdefault.jpg
0

(26) While vs For vs Goto-Programme

Teil der Vorlesung “Theoretische Informatik”, Sommersemester 2021, Ulrike von Luxburg, Uni Tübingen. Source of this “Tübingen Machine Learning” AI Video
1635190868_maxresdefault.jpg
198
55:41

TensorFlow.js: Make a smart webcam in JS with a pre-trained ML model | Workshop

Learn how to detect over 80 common objects in real time by using a TensorFlow.js pre-trained model in your web browser to give your next web application superpowers. We walk through an end-to-end creation of a smart camera in this Workshop. Resources: What’s new in TensorFlow.js? Machine learning for next gen web apps → https://goo.gle/3v6cwBg […]
1635181414_maxresdefault.jpg
190
10:27

PyTorch and Keras TensorFlow for the Next 3 Years, Reflections from GTC 2021

Several presentations at GTC-21 discussed the next 3-5 year direction for PyTorch and Keras/Tensorflow. In this video, I summarize what is ahead for these important frameworks. Presentations referenced: François Chollet Soumith Chintala https://www.nvidia.com/en-us/gtc/topics/ Follow Me/Subscribe: https://www.youtube.com/user/HeatonResearch https://github.com/jeffheaton Tweets by jeffheaton Support Me on Patreon: https://www.patreon.com/jeffheaton Source of this machine learning/AI Video
1635162965_maxresdefault.jpg
15
02:28:53

Neural Compression — Lecture 4 — Random Variables and Autoregressive Models

Fourth week 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. Viewers who are […]
1635161866_maxresdefault.jpg
12
01:00:05

Causal Modeling in Machine Learning with Robert Ness 5/27/21

Causality and probabilistic modeling are some of the hottest topics in machine learning. In early 2020 we launched a new cohort-based course on the topic with instructor Robert Osazuwa Ness. The course has received great feedback from students: “I liked the workshop very much. Robert did a great job of reaching out to students to […]
1635122360_maxresdefault.jpg
14
02:21:32

Neural Compression — Lectures 6 & 7 — Stream Codes I: Asymmetric Numeral Systems (ANS)

Sixth and seventh week 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 […]
1635107659_maxresdefault.jpg
20
03:59

ICML 2021: Bayesian Quadrature on Riemannian Data Manifolds

——————————————————————————– Bayesian Quadrature on Riemannian Manifolds Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis International Conference on Machine Learning (ICML) 2021 ——————————————————————————– ► Paper: https://arxiv.org/abs/2102.06645 ► Code: github.com/froec/BQonRDM. Riemannian manifolds provide a principled way to model nonlinear geometric structure inherent in data. A Riemannian metric on said manifolds determines geometry-aware shortest paths and […]
1635098473_maxresdefault.jpg
252
15:04

Machine learning for next gen web apps with TensorFlow.js | Session

Get a high level overview of what TensorFlow.js is, how it’s currently being used, what’s new this year, our plans for the future, and how you can get involved with our newly formed special interest and working groups. This Session is suitable for everyone. Resources: Join us for an Ask me anything Q&A → https://goo.gle/3h4JSfR […]
1635095537_maxresdefault.jpg
3
39:33

Learning Long-Time Dependencies with RNNs w/ Konstantin Rusch – #484

Today we conclude our 2021 ICLR coverage joined by Konstantin Rusch, a Ph.D. Student at ETH Zurich. In our conversation with Konstantin, we explore his recent papers, titled coRNN and uniCORNN respectively, which focus on a novel architecture of recurrent neural networks for learning long-time dependencies. We explore the inspiration he drew from neuroscience when […]
1635095139_maxresdefault.jpg
29
00:14

Should You Still Learn ML In 2021? #Shorts

My opinion if you should still study Machine Learning in 2021?! If you enjoyed this video, please subscribe to the channel: ▶️ : https://www.youtube.com/channel/UCbXgNpp0jedKWcQiULLbDTA?sub_confirmation=1 ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~ 🖥️ Website: https://www.python-engineer.com 🐦 Twitter – https://twitter.com/python_engineer ✉️ Newsletter – https://www.python-engineer.com/newsletter 📸 Instagram – https://www.instagram.com/patloeber 🦾 Discord: https://discord.gg/FHMg9tKFSN ▶️ Subscribe: https://www.youtube.com/channel/UCbXgNpp0jedKWcQiULLbDTA?sub_confirmation=1 ~~~~~~~~~~~~~~ SUPPORT ME ~~~~~~~~~~~~~~ 🅿 Patreon – […]
1635085695_maxresdefault.jpg
32
07:03

NeurIPS 2021: Cockpit: A Practical Debugging Tool for Training Deep Neural Networks

——————————————————————————– Cockpit: A Practical Debugging Tool for Training Deep Neural Networks Frank Schneider, Felix Dangel, and Philipp Hennig Advances in Neural Information Processing Systems (NeurIPS) 2021 ——————————————————————————– ► Paper: https://arxiv.org/abs/2102.06604 ► Cockpit Code: https://github.com/f-dangel/cockpit ► Try it: pip install cockpit-for-pytorch When engineers train deep learning models, they are very much “flying blind”. Commonly used methods […]
1635078376_maxresdefault.jpg
15
09:10

Generalization in data-driven models of primary visual cortex (ICLR 2021 Spotlight)

First author Konstantin-Klemens Lurz from the Neuronal Intelligence Lab (https://sinzlab.org/) gives a short overview of his work on generalizing models of visual cortex. Spotlight talk at ICLR 2021. *Paper*: (official publication at ICLR in May 2021) https://openreview.net/forum?id=Tp7kI90Htd The *dataset* of the mouse that we test the generalization performance of our representation on: https://gin.g-node.org/cajal/Lurz2020 *Code* with […]
1635061385_maxresdefault.jpg
244
12:22

ML Kit: Turnkey APIs to use on-device ML in mobile apps | Session

Machine Learning Kit (ML Kit) is an on-device Software Development Kit (SDK) for mobile developers to add Google’s machine learning expertise to their mobile apps easily. In this Session, we go over what’s new in the world of on-device ML and also showcase how simple it is to build an app using the ML Kit. […]
1635033492_maxresdefault.jpg
203
17:29

Applications of Deep Neural Networks Course Overview (1.1, Spring 2021)

Spring 2021 Version. Applications of deep neural networks is a course offered in a hybrid format by Washington University in St. Louis. This course introduces Keras deep neural networks and highlights applications that neural networks are particularly adept at handling compared to previous machine learning models. Deep learning is a group of exciting new technologies […]
1635019058_maxresdefault.jpg
19
01:09:02

Neural Compression — Lecture 2 — Theoretical Bounds for Lossless Compression

Second week 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 entire […]
1635007843_maxresdefault.jpg
0
45:15

(22) Satz von Rice

Teil der Vorlesung “Theoretische Informatik”, Sommersemester 2021, Ulrike von Luxburg, Uni Tübingen Source of this “Tübingen Machine Learning” AI Video
1635004150_maxresdefault.jpg
7
01:19:58

Probabilistic ML — Lecture 21 — Efficient Inference and k-Means

This is the twentyfirst lecture in the Probabilistic ML class of Prof. Dr. Philipp Hennig, updated for the Summer Term 2021 at the University of Tübingen. Slides available at https://uni-tuebingen.de/en/180804. Contents: * Collapsed Gibbs Sampling * k-Means * Lyapunov Functions © Philipp Hennig / University of Tübingen, 2021 CC BY-NC-SA 3.0 Source of this “Tübingen […]