- 90
- 510 915
Steven Van Vaerenbergh
เข้าร่วมเมื่อ 5 ก.ย. 2013
Educational videos about machine learning.
RevEye Reverse Image Search 2
The RevEye Reverse Image Search Chrome extension allows to perform an inverse image search by right-clicking onto any image in a web site. Included image search engines: Google, Bing, Yandex, TinEye and Baidu. Go to the options page to add more search engines.
PS: Feeling inspired? Sing along!
In this world of endless images, there's a tool you ought to know
For journalists and truth seekers, it's the way to go
Artists and creatives, listen to what I say
RevEye's here to help you find the truth today
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
Google, Bing, and Yandex, TinEye's in the mix
Choose your favorite engine, or use 'em all for kicks
Customize your options, tailor it to your need
RevEye's fast and friendly, it'll help you succeed
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
But wait, there's more, if you're feeling bold
Add your own search engine, let your story be told
In the options page, it's easy to do
RevEye's flexible, just like you
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
So next time you're wondering where that image came from
Remember RevEye, and your search will be done
PS: Feeling inspired? Sing along!
In this world of endless images, there's a tool you ought to know
For journalists and truth seekers, it's the way to go
Artists and creatives, listen to what I say
RevEye's here to help you find the truth today
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
Google, Bing, and Yandex, TinEye's in the mix
Choose your favorite engine, or use 'em all for kicks
Customize your options, tailor it to your need
RevEye's fast and friendly, it'll help you succeed
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
But wait, there's more, if you're feeling bold
Add your own search engine, let your story be told
In the options page, it's easy to do
RevEye's flexible, just like you
Oh, RevEye, RevEye, reverse image search
Find the source, solve the mystery, be the first
Right-click that picture, let the engines run
RevEye's got your back, till the job is done
So next time you're wondering where that image came from
Remember RevEye, and your search will be done
มุมมอง: 1 025
วีดีโอ
ChatGPT 4 system prompt (December 16, 2023)
มุมมอง 201ปีที่แล้ว
The system prompt is the initial prompt in each conversation of ChatGPT. Here, shown for ChatGPT 4. For ChatGPT 3.5, see this video: th-cam.com/video/g05zJnukTcg/w-d-xo.html
ChatGPT 3.5 system prompt (December 16, 2023)
มุมมอง 59ปีที่แล้ว
The system prompt is the initial prompt in each conversation of ChatGPT. Here, shown for ChatGPT 3.5. For ChatGPT 4, see this video: th-cam.com/video/QJkul4DWbiY/w-d-xo.html
GitHub Copilot demonstration October 2023 (part 2)
มุมมอง 476ปีที่แล้ว
Asking GitHub Copilot add a data classifier to an existing script.
GitHub Copilot demonstration October 2023 (part 1)
มุมมอง 345ปีที่แล้ว
Asking GitHub Copilot add a data classifier to an existing script.
Demo of ChatGPT's visual capabilities (Oct. 2023)
มุมมอง 406ปีที่แล้ว
I drew a machine learning pipeline on a whiteboard and checked if ChatGPT could turn the picture into Python code... and it just did so.
Demo of ChatGPT's Advanced Data Analysis (Oct. 2023)
มุมมอง 276ปีที่แล้ว
A short demonstration showing an exploratory data analysis using ChatGPT's Advanced Data Analysis mode (previously known as "Code Interpreter").
Geometric reasoning with ChatGPT and GeoGebra, part 2
มุมมอง 446ปีที่แล้ว
I asked ChatGPT to create a rectangular triangle in GeoGebra, using only basic drawing tools. It did not find a correct solution. Previous try using GPT 3.5: th-cam.com/video/DKV_XcZKg0A/w-d-xo.html Prompt: "Give me the steps in GeoGebra to draw a rectangular triangle. Use only the following tools: point, polygon, intersect, line, segment, circle with center through point, polygon. Make sure ea...
ChatGPT 3 minute presentation
มุมมอง 389ปีที่แล้ว
Prompt: Can you help me create a 3 minute presentation on ChatGPT? For a general audience, list key points and time allocation, use markdown.
Copilot demonstration April 2023
มุมมอง 127ปีที่แล้ว
Using GitHub Copilot to write a script that loads data from a file, plots it, and then trains a support vector machine on the data (80-20 split). Finally, a second plot is made with the decision boundaries, and the accuracy is reported. No audio.
Using ChatPDF to chat with an astrophysics paper
มุมมอง 77ปีที่แล้ว
Using ChatPDF to chat with an astrophysics paper
Using D-ID to create a talking avatar video
มุมมอง 663ปีที่แล้ว
Using D-ID to create a talking avatar video
Using ChatPDF to automatically generate Python code from pseudocode in an academic article
มุมมอง 391ปีที่แล้ว
Using ChatPDF to automatically generate Python code from pseudocode in an academic article
Geometric reasoning with ChatGPT and GeoGebra, part 1
มุมมอง 1.4K2 ปีที่แล้ว
Geometric reasoning with ChatGPT and GeoGebra, part 1
Aki Vehtari: Stan and probabilistic programming (MLSP 2020 tutorial)
มุมมอง 6294 ปีที่แล้ว
Aki Vehtari: Stan and probabilistic programming (MLSP 2020 tutorial)
Razvan Pascanu: Improving learning efficiency for deep neural networks (MLSP 2020 keynote)
มุมมอง 3724 ปีที่แล้ว
Razvan Pascanu: Improving learning efficiency for deep neural networks (MLSP 2020 keynote)
Ole Winther: Latent variable models from independent components to VAEs and flows (MLSP2020 keynote)
มุมมอง 5434 ปีที่แล้ว
Ole Winther: Latent variable models from independent components to VAEs and flows (MLSP2020 keynote)
Michael Unser: Splines and Machine Learning: From classical RKHS methods to DNN (MLSP 2020 keynote)
มุมมอง 9724 ปีที่แล้ว
Michael Unser: Splines and Machine Learning: From classical RKHS methods to DNN (MLSP 2020 keynote)
Truyen Tran - Learning to Remember More with Less Memorization (ICLR 2019 talk)
มุมมอง 2854 ปีที่แล้ว
Truyen Tran - Learning to Remember More with Less Memorization (ICLR 2019 talk)
Robert Geirhos: ImageNet-trained CNNs are biased towards texture (ICLR 2019 talk)
มุมมอง 2.2K4 ปีที่แล้ว
Robert Geirhos: ImageNet-trained CNNs are biased towards texture (ICLR 2019 talk)
John M. Abowd: The U.S. Census Bureau Tries to be a Good Data Steward in the 21st Century
มุมมอง 1.2K5 ปีที่แล้ว
John M. Abowd: The U.S. Census Bureau Tries to be a Good Data Steward in the 21st Century
ICLR Debate with Leslie Kaelbling (ICLR 2019)
มุมมอง 2.9K5 ปีที่แล้ว
ICLR Debate with Leslie Kaelbling (ICLR 2019)
Yikang Shen: Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (ICLR2019)
มุมมอง 2.2K5 ปีที่แล้ว
Yikang Shen: Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (ICLR2019)
Pierre-Yves Oudeyer: Developmental Autonomous Learning (ICLR 2019 invited talk)
มุมมอง 6715 ปีที่แล้ว
Pierre-Yves Oudeyer: Developmental Autonomous Learning (ICLR 2019 invited talk)
Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)
มุมมอง 48K5 ปีที่แล้ว
Ian Goodfellow: Adversarial Machine Learning (ICLR 2019 invited talk)
J. Frankle & M. Carbin: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
มุมมอง 18K5 ปีที่แล้ว
J. Frankle & M. Carbin: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Susan Athey: Counterfactual Inference (NeurIPS 2018 Tutorial)
มุมมอง 10K6 ปีที่แล้ว
Susan Athey: Counterfactual Inference (NeurIPS 2018 Tutorial)
Alex Graves and Marc'Aurelio Ranzato: Unsupervised Deep Learning (NeurIPS 2018 Tutorial)
มุมมอง 3.1K6 ปีที่แล้ว
Alex Graves and Marc'Aurelio Ranzato: Unsupervised Deep Learning (NeurIPS 2018 Tutorial)
Frank Hutter and Joaquin Vanschoren: Automatic Machine Learning (NeurIPS 2018 Tutorial)
มุมมอง 7K6 ปีที่แล้ว
Frank Hutter and Joaquin Vanschoren: Automatic Machine Learning (NeurIPS 2018 Tutorial)
Thanks Schmidhuber I had the same questions while reading the paper.....
then I read the final copy 😂
Schmidhuber sounds bitter😅
That's just sampling with a new name. The innovation is in naming, not method.
Has anyone kept track of the plagiarism Jürgen mentioned and if they are actually based on facts? Because he does make good points. We should not allow accidental/plagiarism and corrections have to be made.
👍👍👍👍
Jones Brian Smith Kenneth Thomas Donna
Schmidhuber putting the ADVERSERIAL in GANs @ 1:03:00
Where is that music from? Love it
Lol. That's "Insensatez" by Antonio Carlos Jobim
My role model we are science 🔭🧪
Neurosymbolic and Heterogenous Modalities are needed
Excellent presentation ❤❤
This is such an amazing introduction to this topic!
👍👍👍👍👍👍
Its super depressing
Agree with you..i have asked Chat GPT but gave me the wrong syntax
I was recently scammed. I used a reverse image app and found out that I was catfished. So how do I find out the real person I was talking to
Not convinced. Does it run correctly - lol
I read about him and looked him up on TH-cam. Brilliance and speech is in UNION
Good one
sometimes, geogebra give me a code to input on geogebra. Do you know, how to input that code?
There should be an input field on the bottom of the window.
"Exsetra.... exsetra... exsetra..." The word is ET-CET-ER-A!
Great musical taste!
Hey thanks for the cool chrome extension, made life a bit easier
I dont think people realize this is one of the most important lectures in the past 100 years... GAN... it will be everywhere soon.
who is using gans?
gans are dead lol
Lol
52 million is about as much as Spain 🤓
Would be good to see a comparison with European census practices, which instead evolved to use no field surveys and instead perform all the statistics based on the data on interconnected government information systems.
18:03
very informative and inspirational talk
For more information check out this video! th-cam.com/video/Qnu0thrtV6A/w-d-xo.html
RAHHHHHH I LOVE AMERICA!!!! I HATE THE ISIS
13:24 when searching for the best theta, Ian is summing over the log of the probabilities rather than over the probabilities, why?
If it's still relevant, I'll try to help. This is called maximum likelyhood estimation, which is the product of the estimated probabilities on the training dataset. As derivative of product is not easy to work with, we take a log of this, so this yields the sum of logs. As log is a monotonous function it doesn't change the local minimum and is easier to take the derivative of. Hope it helped
NeurIPS tutorial always great!
30:00 The most intuitive explaination for stochastic optimization I have ever heard so far.
you can use traditional econometric tools as well ( as it was formerly known as 'econometrics', and not ' data science') btw when i see the questions regarding time series on AI forums, i have absolutely no doubt that nobody will get what a garch process is, neither a garch-m ( which was developped, as i can remember it... by andrew ng) cheers
Very well organised lecture, thank you Ian!
😂
13:53 老弟真的没礼貌
Hello do you like to play lottery pick 3?
@@justinking5964 Never played it. Why?
@@hangchen I assumed you are not American. Just ask randomly.
@@justinking5964 Lol yea your assumption is correct. Do most Americans play lottery pick 3?
Really clear! Best tutorial to talk about the relationship between optimal control and reinforcement learning I've ever seen!
Well well well another prodigy from stanford that has made a.i more complicated and sophisticated for the better good of humanity 😔... Isnt GAN whats CONDUCTING the war now lol 😂. I remember movie WARGAMES
TO FLORENTINO S. SUSALO III. THANK YOU FOR COURTING ME. EVEN THOUGH YOU ARE A LESS FORTUNATE. I KNOW YOU TRULY LOVE ME. HE COURTED ME DECENTLY. THANK YOU FLORENTINO S. SUSALO III FOR ALL THE SACRIFICES. THE LLUSTRISSIMO FAMILY BACKGROUND JUST LIKES THE PROPERTIES FROM MANILA TO ZAMBOANGA CITY. RACHEL LU STARTED IT BACK IN 2013 IN ZAMBOANGA CITY WATER DISTRICT COMPANY.
RACHEL LU JUST LIKES THE PROPERTIES FROM MANILA TO ZAMBOANGA CITY. THE LLUSTRISSIMO FAMILY BACKGROUND ARE INSINCERE. FLORENTINO S. SUSALO III DIDN'T LET ME SPEND WHEN HE COURTED ME.
I KNOW JOHN PLATT WHEN FLORENTINO S. SUSALO III COURTED ME. I KNOW FLORENTINO S. SUSALO III IS SINCERE. THE LLUSTRISSIMO FAMILY BACKGROUND JUST LIKES THE PROPERTIES FROM MANILA TO ZAMBOANGA CITY. THE LLUSTRISSIMO FAMILY BACKGROUND ARE INSINCERE.
i came here just to understand GANs a bit better, didn't realize i would strike gold at 1:03:00
Can you give your study plan as in how do you get it?
@@kanishktantia7899 just watch a couple of videos on this, derive the min-max loss atleast once on paper. See a basic implementation of GAN from scratch. I was doing it just for making a ppt on a research paper (StyleGAN2), so this was more than enough for me. Same goes for any other topic in DL. I was just dipping my feet in the deep sea of DL, i ain't touching it again.
@@ruchirjain1163 Sure , that might help. Im looking for higher study opportunities from abroad in this space only. Can you help me in any capacity?
@@kanishktantia7899 it depends mate, i would say you should try going for thesis if u have that in ur university
@@ruchirjain1163 I graduated last year, working these days.. not enrolled currently at any university..I'm looking for that only. Any lab or any university in US or maybe somewhere else.
Why make it simple when you can make it complicated !
Great talk
31:09 onwards for the deeper dive
At 10:52 back in the day when I was in form two secondary school; our Math teacher challenged us to find integer x in the equation: 2^2 + 3^2 = x^2. I wish I knew Fermat's last theorem. I never forget that equation!
Where can we get the photos from the slides?
This ian kid is rude and not so goodfellow. Schmidhuber politely just asked a question and got attacked
And also schmidhuber can be his father, he should show a little more respect
@@EB3103 Ok boomer
We're talking about a guy that says he invented "generative adversarial networks", when the paper clearly mentions 7 other people, university staff and more working on the project. Of course he's gonna talk like that.
@@Nickyreaper2008 He also likes to call himself "The industry lead"