I'm excited about recent developments in NLP, deep RL, speeding up training/inference, big GANs, powerful DL frameworks, and real-world application of DL in driving 370k+ Tesla HW2 cars! What else would you like to see covered?
Didn't understand much. But I'm excited. Moving forwards.
Super talk, keep up the good job.
Amazing content Lex, always very informative to help filter the firehose of research papers.
Thanks for the lecture. Also, well edited (erasing pauses). Funny to see you transform to Men in Blue compared to when you started the lecture two years ago. Looking good
Thanks a ton Lex! You're one of the guys who brought me from Mech. Engineering to AI 🙂
So funny how Lex refers to the fast.ai folks as renegade reserchers 😀
No "Ums" and "Aws" for Lex. Good speaker.
This is fantastic. I am trying to create a storytelling system using LSTM s and a corpus of self-written works. Thank you for this Mr. Fridman.
GOOD Thanks a lot !
Would you please make a video detailed lecture on computer vision and algorithm for real time tracking applications?
Multi scale processing seems a great baseline
No nonsense AI from Lex
Is there a way to solve the need for so much data?
It would be great if you add to description links from the presentation!
This is attempting computational expression! It inhibits natural inherent algorithmic processing. Human is an emotional cognitive being. Whether it be locution or calculation, induction/deduction is based on emotional cognitive aptitude, therewith conflict with the attempt of mimicking sterile computation and natural anatomization. I have watched from afar and Chomsky is aware who I am… ( ^V^ ) If human continues to use technology without the comprehension that tech creates an ersatz structure, than human will fall deeper and deeper into a form of psychosis. Love to ALL
Great review on recent advance in deep learning! Would be great to see a similar review of current (immediate) challenges e.g. limited numerical extrapolation abilities, multi-task learning…etc.
BLOW MIND!!!!. I have a question. To simulate the human brain you also may need to simulated the human body because many of those connection I believe comes from the organs that the brain is sustaining to keep it alive. Plus in the human body depending of the blood flow, the toxin of the blood, the well of the organs, the air that the lung use, almost everything on the organ affect the function of the brain work. Plus, with the 100 billion neuron with more than 1 trillion connection in the brain. SO, do you think that after all that research of the human connection it also has to be done a research of the human body to simulate inside a computer?.
I was absolutely shocked by how brilliant these approaches to deep learning where. I'm absolutely excited to see what we can come up with next
adanet is very interesting! that is a very good material on progressive learning for data scarse situation! also multiple classification in rounds… and one on confusion for fine grain classifications without augmentation!
multi complex layer systems are the future, they can be called deep complex neural networks. what I mean by that is, on each layer (to accelerate processing, inference or probable future AI applications) it is possible to train the same dataset for many different inputs, for example, it is possible to train a dataset with a video file, equipped with IMU data, with MIC input and system can learn, what type of orientation of the IMU can cause audio level breaks and what type of high-speed angle changes can cause over or under exposures. we are working on those issues with HDR capable sensors to get always-perfect image and near-perfect audio with mutiple level microphone inputs. similar techniques can be applied to autonomous driving, medical robots or self driving rovers on moon or mars.
Does anyone know what technology amazon textract uses?
Very happy to see the prosperity of deep learning. I hope I can excavate the biggest potential of DL in the field of computational advertising.
If this lecture is over my head and I need a little more knowledge about the fundamental concepts where should I look for that?
Thanks for the video. It will be the primary resource for our event: https://www.meetup.com/Paris-Machine-Learning-Study-Group-in-English-Meetup/events/tlzcqqyzdbhb/
I think he speeks more faster than before
I see a hand-waving review of acronyms and no step-by-step tracing of algorithms. No substance. NeXT!
So, the AutoAugment is about augmentation of worst possible inputs? Like you try to do augmented ops that are hardest to recognize correctly thus force network to learn them better?
This is the most valuable thing that I saw in 2019.
Lex's summary is so true:Stochastic gradient descent and backpropagation are still backbones of the current state of the art AI techniques. Therefore, we need some innovations to see leaps in the field.Thank you Lex!
Dressing like the men in black isn't helping….
"The way you achieve great things is you try." — Lex Fridman
It could be very insightful to go back to this talk in a couple of years time, and see how these ideas developped.
Awesome video. Are there good links to videos on other developments not mentioned, e.g. in healthcare and agriculture?
This guy have the same voice that the Breaking Bad's actor, Jesse Pinkman.
This is the most valuable thing that I saw in 2019.This guy have the same voice that the Breaking Bad's actor, Jesse Pinkman.
Thank you Lex !! Always great to learn from you
45:06 I am a student deeply suspicious of everything Geoff Hinton has said. The future depends on me. I am John Connor.
I only completed watching this video because I think he is charming.
We should not "throw it all away and start over" as Hinton suggested, I am totally against this idea. For one thing, we have no prove whether back-propagation is not there since we have very limited understandings of how the human brain works, and recent advancement of Deep Learning proves that it simply works and works exceedingly well in many domains, so the world should thrown in more resources and do whatever possible to exploit these 60's and 80's good tricks, on the other hand, we should be deeply suspicious everything Hinton said (as he suggested) because we know Machine Learning is rooted on something fundamentally limited itself, be it "XOR-problem", lack of rule-based AI capabilities, explanation etc and come up with with radically new different approaches for address new problems. P.S. For my first point, I am actually applying Hinton's second statement onto his first statement.
Your email address will not be published. Required fields are marked *
Save my name, email, and website in this browser for the next time I comment.