![Jon Krohn](/img/default-banner.jpg)
- Видео 143
- Просмотров 1 170 590
Jon Krohn
Добавлен 13 июл 2013
Dr. Jon Krohn is Chief Data Scientist at Nebula, author of the bestselling book Deep Learning Illustrated, and host of the SuperDataScience podcast. Jon is renowned for his compelling lectures, which he offers in-person at Columbia University, New York University, and leading industry conferences.
Copies of Deep Learning Illustrated are available at bit.ly/iTkrohn. Use KROHN during checkout for 35% off!
Also available from Amazon at amzn.to/32TB6rB
To keep up with the latest from Jon, sign up for his newsletter here at jonkrohn.com, follow him on Twitter @JonKrohnLearns, and on LinkedIn at linkedin.com/in/jonkrohn.
Copies of Deep Learning Illustrated are available at bit.ly/iTkrohn. Use KROHN during checkout for 35% off!
Also available from Amazon at amzn.to/32TB6rB
To keep up with the latest from Jon, sign up for his newsletter here at jonkrohn.com, follow him on Twitter @JonKrohnLearns, and on LinkedIn at linkedin.com/in/jonkrohn.
Generative AI with Large Language Models: Hands-On Training feat. Hugging Face and PyTorch Lightning
TOPIC SUMMARY
Module 1: Introduction to Large Language Models (LLMs)
- A Brief History of Natural Language Processing (NLP)
- Transformers
- Subword Tokenization
- Autoregressive vs Autoencoding Models
- ELMo, BERT and T5
- The GPT (Generative Pre-trained Transformer) Family
- LLM Application Areas
Module 2: The Breadth of LLM Capabilities
- LLM Playgrounds
- Staggering GPT-Family progress
- Key Updates with GPT-4
- Calling OpenAI APIs, including GPT-4
Module 3: Training and Deploying LLMs
- Hardware Options (e.g., CPU, GPU, TPU, IPU, AWS chips)
- The Hugging Face Transformers Library
- Best Practices for Efficient LLM Training
- Parameter-efficient fine-tuning (PEFT) with low-rank adaptation (LoRA)
- Open-...
Module 1: Introduction to Large Language Models (LLMs)
- A Brief History of Natural Language Processing (NLP)
- Transformers
- Subword Tokenization
- Autoregressive vs Autoencoding Models
- ELMo, BERT and T5
- The GPT (Generative Pre-trained Transformer) Family
- LLM Application Areas
Module 2: The Breadth of LLM Capabilities
- LLM Playgrounds
- Staggering GPT-Family progress
- Key Updates with GPT-4
- Calling OpenAI APIs, including GPT-4
Module 3: Training and Deploying LLMs
- Hardware Options (e.g., CPU, GPU, TPU, IPU, AWS chips)
- The Hugging Face Transformers Library
- Best Practices for Efficient LLM Training
- Parameter-efficient fine-tuning (PEFT) with low-rank adaptation (LoRA)
- Open-...
Просмотров: 21 999
Видео
Getting Value from Artificial Intelligence - Jon Krohn at Hg Capital "Digital Forum" 2023
Просмотров 2,2 тыс.Год назад
In February 2023, I delivered this keynote on "Getting Value from A.I." to open the second day of Hg Capital's "Digital Forum" in London. With a focus on B2B SaaS applications, over 45 minutes I covered: 1. What Deep Learning A.I. is and How it Works 2. Tasks that are Replaceable with A.I. vs Tasks that can be Augmented 3. How to Effectively Implement A.I. Research into Production The audience ...
Four Major Weightlifting PRs (DL, OHS, PJ, FS)
Просмотров 1,7 тыс.Год назад
New year, same process... and incrementally more results (in this case, weightlifting PRs). By sticking to my never-miss-a-workout habit since Autumn 2020, these most recent weightlifting personal records - shown in the video and all done on different days in recent weeks - are: • Deadlift: 455lb. ( 15lb. over May 2022) • Overhead Squat: 200lb. ( 10lb. over May 2022) • Push Jerk: 230lb. ( 10lb....
#shorts Plotting a System of Linear Equations
Просмотров 287Год назад
My "Machine Learning Foundations" RUclips series covers the foundational subjects you need to excel at ML. In the second episode of the series I walk through how to plot a system of linear equations in Python! Full video here: ruclips.net/video/ibTYANFwrNc/видео.html #ML #algebra #linearalgebra
#Shorts System of Linear Equations - Topic 1 of Machine Learning Foundations
Просмотров 251Год назад
In this clip I walkthrough a system of linear equations problem. The full video is the first video of my Machine Learning Foundations series, where I introduce the basics of Linear Algebra and how Linear Algebra relates to Machine Learning, as well as providing a brief lesson on the origins and applications of modern algebra. There are eight subjects covered comprehensively in the ML Foundation...
The Staggering Pace of Technological Change in One Lifetime
Просмотров 749Год назад
My first TED-format talk is live! In it, I use (A.I.-generated!) visuals to color how A.I. will transform the world in our lifetimes, with particular emphases on climate change, food security, and healthcare innovations. This clip is the opening hook of the talk. For the full video, head over to: jonkrohn.com/TEDx
Big Olympic Lift PRs: 255# Clean & 185# Snatch
Просмотров 982Год назад
One year into disciplined commitment to a CrossFit training program, the gains have mostly been slow and modest, but they suddenly started accumulating to great effect. My previous clean PR was just 235 pounds, so this is a whopping 20-pound jump to 255#. Similarly surprising (you can see from my reaction in the video!) the 185-pound snatch was an enormous 15# jump over my previous PR of 170#.
380# Back Squat & 170# Snatch: New All-Time PRs
Просмотров 1,1 тыс.2 года назад
Last week I set new all-time PRs for two lifts: the back squat and snatch. I failed both lifts on my first attempt. However, I was able to overcome mental hurdles and succeeded on the second attempt at hitting new all-time PRs in both lifts: 380# back squat (compared to 375# in December) 170# snatch (compared to 160# in December)
440-pound Deadlift: First Lift 2x Bodyweight
Просмотров 1,7 тыс.2 года назад
I weigh 220 pounds so this 440-pound deadlift is my first ever of twice my bodyweight and a new all-time PR. My previous PR was 405 pounds in May 2021; delighted to crush that figure a year later :)
Exercises on Event Probabilities - Topic 98 of Machine Learning Foundations
Просмотров 2,9 тыс.2 года назад
#MLFoundations #Probability #MachineLearning In my series of videos on Probability Theory we’ve already covered events, sample spaces, multiple observations, and combinatorics. This video features four exercises - some using paper and pencil, some using Python code - to test and cement your understanding of the topics so far. There are eight subjects covered comprehensively in the ML Foundation...
Combinatorics - Topic 97 of Machine Learning Foundations
Просмотров 2,6 тыс.2 года назад
#MLFoundations #Probability #MachineLearning Combinatorics is a field of mathematics devoted to counting that can be helpful for studying probabilities. In this video, we use examples with real numbers to bring this combinatorics field to life and relate it to probability theory. There are eight subjects covered comprehensively in the ML Foundations series and this video is from the fifth subje...
Multiple Independent Observations - Topic 96 of Machine Learning Foundations
Просмотров 2,3 тыс.2 года назад
#MLFoundations #Probability #MachineLearning In this video, we consider probabilistic events where we have multiple independent observations - such as flipping a coin two or more times instead of just once. There are eight subjects covered comprehensively in the ML Foundations series and this video is from the fifth subject, "Probability & Information Theory". More detail about the series and a...
Events and Sample Spaces - Topic 95 of Machine Learning Foundations
Просмотров 3,4 тыс.2 года назад
#MLFoundations #Probability #MachineLearning In this video, we learn about some of the most fundamental atoms of probability theory: events and sample spaces. There are eight subjects covered comprehensively in the ML Foundations series and this video is from the fifth subject, "Probability & Information Theory". More detail about the series and all of the associated open-source code is availab...
What Probability Theory Is - Topic 94 of Machine Learning Foundations
Просмотров 5 тыс.2 года назад
#MLFoundations #Probability #MachineLearning This video is a quick introduction to what Probability Theory is! There are eight subjects covered comprehensively in the ML Foundations series and this video is from the fifth subject, "Probability & Information Theory". More detail about the series and all of the associated open-source code is available at github.com/jonkrohn/ML-foundations The pla...
A Brief History of Probability Theory - Topic 93 of Machine Learning Foundations
Просмотров 9 тыс.2 года назад
#MLFoundations #Probability #MachineLearning This video is a quick introduction to the fascinating history of Probability Theory. There are eight subjects covered comprehensively in the ML Foundations series and this video is from the fifth subject, "Probability & Information Theory". More detail about the series and all of the associated open-source code is available at github.com/jonkrohn/ML-...
Probability & Information Theory - Subject 5 of Machine Learning Foundations
Просмотров 15 тыс.2 года назад
Probability & Information Theory - Subject 5 of Machine Learning Foundations
My Favorite Calculus Resources - Topic 92 of Machine Learning Foundations
Просмотров 2,4 тыс.2 года назад
My Favorite Calculus Resources - Topic 92 of Machine Learning Foundations
Finding the Area Under the ROC Curve - Topic 91 of Machine Learning Foundations
Просмотров 2 тыс.2 года назад
Finding the Area Under the ROC Curve - Topic 91 of Machine Learning Foundations
Definite Integral Exercise - Topic 90 of Machine Learning Foundations
Просмотров 1,4 тыс.2 года назад
Definite Integral Exercise - Topic 90 of Machine Learning Foundations
Numeric Integration with Python - Topic 89 of Machine Learning Foundations
Просмотров 1,5 тыс.2 года назад
Numeric Integration with Python - Topic 89 of Machine Learning Foundations
Definite Integrals - Topic 88 of Machine Learning Foundations
Просмотров 1,4 тыс.2 года назад
Definite Integrals - Topic 88 of Machine Learning Foundations
Indefinite Integral Exercises - Topic 87 of Machine Learning Foundations
Просмотров 1,2 тыс.2 года назад
Indefinite Integral Exercises - Topic 87 of Machine Learning Foundations
The Integral Calculus Rules - Topic 86 of Machine Learning Foundations
Просмотров 1,4 тыс.2 года назад
The Integral Calculus Rules - Topic 86 of Machine Learning Foundations
What Integral Calculus Is - Topic 85 of Machine Learning Foundations
Просмотров 1,9 тыс.2 года назад
What Integral Calculus Is - Topic 85 of Machine Learning Foundations
The ROC Curve (Receiver-Operating Characteristic Curve) - Topic 84 of Machine Learning Foundations
Просмотров 2,5 тыс.2 года назад
The ROC Curve (Receiver-Operating Characteristic Curve) - Topic 84 of Machine Learning Foundations
The Confusion Matrix - Topic 83 of Machine Learning Foundations
Просмотров 1,6 тыс.2 года назад
The Confusion Matrix - Topic 83 of Machine Learning Foundations
Binary Classification - Topic 82 of Machine Learning Foundations
Просмотров 1,7 тыс.2 года назад
Binary Classification - Topic 82 of Machine Learning Foundations
Integral Calculus - The Final Segment of Calculus Videos in my ML Foundations Series
Просмотров 1,5 тыс.2 года назад
Integral Calculus - The Final Segment of Calculus Videos in my ML Foundations Series
Exercise on Higher-Order Partial Derivatives - Topic 81 of Machine Learning Foundations
Просмотров 1,2 тыс.2 года назад
Exercise on Higher-Order Partial Derivatives - Topic 81 of Machine Learning Foundations
Thank you, sir
Amazing ❤
i had a doubt , should i complete python first or the lectures?
Johnny sins teaching mathematics😮
5! = 120 . anyway I am waiting for your further videos in this playlist and stats, DSA and most importantly 'Optimization' .
finally I completed this calculas series . thank you Dr. Jon Krohn ❤
By the end of the video (around @9:45), the relationship between (non-zero) singular values to eigendecomposition shouldn't point to eigenVALUES instead of eigenVECTORS?
nice jon well explaiand
❤❤❤❤lovely
if you are looking for a good math for data science of ml these is the best just follow him blindlly...............................................!
Knowing where all of this is applied in the business world, makes it easier to understand. Thank you
It is similar to L2 norm of vectors
Based on the teeth and face movements, if this wasnt 4 years ago I'd say this guy is 100% AI 😂😂
i just came frome 25th video to 1th video just to comment these. if u want to learn math these is the best you can find ...................just blindly follow him
good exp
its just very very good
aaaaan done!
thank you so much John!
yea, this is fun :)
Where is the new video
nailed it!
Thanks Jon Krohn. Do you have a course detailing learning ML from ground up? Thanks in anticipation of your response, I love your pedagogical skills.
i cant get access to your github notebooks it is not loading it says unable to render
Haaa sweet
4:03 can't understand 😢😢
Hi my college restrictions prevent me from accessing the RUclips videos. Are these learning materials available on anyother platform(apart from youtube). Also could you share the playlist's total runtime? As a non-tech background student aiming for AI/ML engineering, would these videos be suitable for beginners? Thank you.
Hi jon, I not able to use no.dot() method for Tensor variable created using PyTorch if the tensor variables in np.dot() method it show Numpy is not available even though it is available
Thanks for including the Origins of Algebra in this lesson. It was a nice interlude and is trivia gold.
Hello sir, Sir I saw your course on udemy about maths for machine learning I want to take that course but udemy is offering a price which exceeds by budget. Sir, if you have a coupon code which can help me board on a flight towards my dream then kindly provide it to me. Thank you sir and have a good day.
jon i cannot find your original repository i can only find clones, could you please send a link, thank you
1 second ago The code in Pytorch is as follows: import torch A_pt = torch.tensor([[-1,2],[3,-2],[5,7]]).float() A_pt U_pt, d_pt, Vt_pt = torch.linalg.svd(A_pt) U_pt_T = U_pt.T V_pt = Vt_pt.T V_pt D_pt = np.diag(d_pt) D_plus_pt = torch.linalg.inv(D_pt) D_conc_plus_pt = torch.concatenate( (D_plus_pt, torch.tensor([[0.],[0.]])), axis=1 ) A_plus_pt = torch.matmul(V_pt, torch.matmul(D_conc_plus_pt ,U_pt_T)) A_plus_pt I am getting the following result: tensor([[-0.0877, 0.1777, 0.0758], [ 0.0766, -0.1193, 0.0869]]) Can somebody please tell if I am correct?
Why didn't you finish this series.
Isnt algerba also geometric?
sorry to say Sir. Since I am watching this series from the beginning, this is the first video difficult to understand for me. if possible Could you teach me even simpler. ( Previous videos are starting with hands on mathematics then move to python code that way of teaching I really liked it , could you include that method for this video too ? )
Hey Jon. I am trying to understand this field of ML and today is my first day. I know basics of programming . Until this video , i've got absolutely no problem and hoping for it to go smooth. My aim is to prepare myself for a job scenario where i might be put into some AIML works . I wanna be pre-proficient with my basics. Have a good day
Thanks , as a maths noobs its a life saver
Hi @JonKrohnLearns Aside from the signs flipping, I also noticed that when i get different outputs when i use P_val, P_vec = np.linalg.eig(P) P_eig_vec = np.dot(P_vec, P_vec.T) {Less Accurate} And P_eig_vec = np.linalg.eig(np.dot(P, P.T)) {More accurate} Like why is that exactly?, it'd do me a great deal if you could tell me why, thanks in advance
please dont give up on this series :')
i loved it its to easy the way you explain it
can we get the course slides?
Thanks a lot for sharing this video. Your videos helped me to understand Algebra concepts, as a beginner. Appreciate your efforts! Now I am a subscriber ( student ) of your channel.
what an incredible video
Just started learning, at video 11 now, very well explained . Thank you
And how much do u weigh?
ngl, everytime tf is looking like "the fc*k" but not tensor flow. 😭😭
new subscriber jon love tje explanation and the video thank you for putting this out here. hope u get more subscribers! came here from Coursera to solve my doubts and now i think ill complete my rest of machine learning course w your videos. thank you
tnk sirr
Love your work !!! Thank you a lot !!!
this video's will use for aiml crouse