Neural Network Architectures u0026 Deep Learning

Video quality	The size	Download

Information Neural Network Architectures u0026 Deep Learning

Title	:	Neural Network Architectures u0026 Deep Learning
Lasting	:	9.09
Date of publication	:
Views	:	812 rb

⛓️⚛️⛓️🔗⛓️🔗⚛️🔗⛓️🔗⛓️🔗〽️⚛️🔂〽️⚛️〽️🔂☯️〽️☯️👁️‍🗨️☯️🕉️☯️🕉️☯️🕉️☯️👁️‍🗨️☸️☯️🕎👁️‍🗨️👁️‍🗨️➿➿👁️‍🗨️🕉️⚛️⚛️⛓️🔗⛓️🔗⛓️🔗⛓️🔗⛓️🔗🔂🔗🔂🔗🔂🔗🔗⛓️🔗🔂🔗⛓️🔗🔗⛓️🔗🔗⛓️🔗🔗⛓️🔗🔂☸️🪯➰🪯🔼➿➿👁️‍🗨️🕎👁️‍🗨️🛐➿◽☦️🔲☦️🛐🔲◽☦️◻️🔲◻️✡️✡️◻️◾◽✡️🔲◽✝️🔼➿🎼➿🔼🔼➰🎼🔼🪯🔼➰➰🛜➰🛐🎼🎼🕉️➰⚕️➰🕉️✡️➰🕉️⚕️☸️🛜🆔➰🛜🆔🆔⚕️🛜〽️🆔🛜🆔🆔〽️〽️🆔〽️⚕️✝️🛐〽️⚕️〽️🆔🛐〽️🆔🛐🛐〽️🆔〽️⚕️🕎⚕️〽️🕎🔘🔲☦️♾️◼️▪️♾️◼️▪️◼️™️▪️◾🔲✝️💟◽🔳👁️‍🗨️🕎➿🛐👁️‍🗨️🔯🪯🔼🔯🔼〽️🔯〽️🔂🔯〽️🔼✴️〽️🔼⛓️🪯🔼⛓️🔼⛓️🪯🛜⛓️🪯🛜⛓️🪯🛜🔂🛜🔂🆔〽️🔂🆔〽️🔂🆔〽️👁️‍🗨️🕎◽🎼➿🎼➿🎼🛐◽🎼◽👁️‍🗨️🕎➿➿🎼🔼🪯🔼➿👁️‍🗨️➿🛜🔂🔯〽️🔂➿🕎🆔〽️🛐🪯〽️🛐〽️🛐🪯✝️🪯〽️🛐✝️〽️✝️👁️‍🗨️✝️👁️‍🗨️✝️👁️‍🗨️✝️⚕️🕉️➰⚕️🕉️➰🕉️⚕️◽🪯🔼⛓️⛓️⛓️🛜⛓️⛓️🔗🔂⚛️⛓️🔗⛓️⚛️⛓️⛓️🔗🔂🔗🔂⚛️⚛️🔂⚕️⛓️⚕️⛓️⛓️⚕️⛓️⛓️⛓️⛓️⚕️⚕️⛓️✴️⚕️⛓️⛓️🎼⛓️🎼⛓️🎼⛓️🎼🎼⛓️🎼🎼⛓️⛓️⛓️⛓️🎼⛓️🔯⚛️⚛️⚛️⚛️⚛️🎼🎼⚛️🔗🎼🎼🎼🔗⚛️✴️🎼🎼🎼🔗🎼🔗⚕️⚕️⛓️⛓️⚕️🔂🔂🔂⚕️⚕️⛓️⛓️⚕️⛓️⚕️🔂🔂🔼⚕️🔼🛜☸️🛜🕎🛜🕎🕎🕎🛜🕎🔂〽️🔼🪯🔼〽️🔂〽️🕎🪯🪯🛐🎼➰◼️➰🕉️◼️➰⚕️🕉️➿💟👁️‍🗨️🛐👁️‍🗨️🕎☯️🕎🛐🔯🔂⚛️⚛️🔂🔯☸️🛐➰🛐🕎➿🕎🕎👁️‍🗨️➿☯️🕎👁️‍🗨️➿◽🕎💟💟🔳💟🔳☦️◽☦️🔲☦️🔲☦️✝️☦️➰⚕️🕉️🎼🎼🎼🕉️⚕️🕉️🎼🕉️🕉️🎼✡️✡️⚕️🕉️✡️⚕️👁️‍🗨️👁️‍🗨️👁️‍🗨️👁️‍🗨️✡️👁️‍🗨️✡️👁️‍🗨️👁️‍🗨️➰🕉️➰🔼🪯➿⚕️☸️☸️🛜⚕️🎼🔯🎼🔼🔼🪯☸️🎼🔼➿🔂👁️‍🗨️🔯🎼🔼🔯〽️🔂⚛️🔂🔯〽️🔯🔂〽️⚛️⛓️🔯🔂🔯⛓️🔯⛓️⛓️⚛️🔂🔂⛓️⚛️⛓️🔗🔗🔯🔯☸️🕎⚕️✡️⚕️🎼◽🛐🎼◽🛐🎼🛐🔲⚕️🕉️🔲🛐☦️◽☦️✝️🔲☦️🔲♾️☦️✝️◻️▪️◻️◾🔲◾😄🔘◾😄◾😃🔘☯️👁️‍🗨️🕎➿👁️‍🗨️➿👁️‍🗨️👁️‍🗨️🕎◽☦️🛐◽💟🕎💟◽✡️🪯🔼🔯〽️🔂🎼➿🎼🔼➿〽️🔂➿🪯🔼➿🪯🔼➿🪯➰🪯🛜➰⚕️🛜➰⚕️🛜➰🛜🆔🛜🆔🆔🛜🆔🆔🛜〽️🕎⚕️〽️⚕️🕎〽️⚕️〽️✡️〽️🔂✴️🔂🔗🔗⛓️🔗🔗⛓️🔂☯️👁️‍🗨️🕎☯️🕉️☯️➿💟🕎➿🕎👁️‍🗨️👁️‍🗨️🔯👁️‍🗨️🔼🔯☯️🕎👁️‍🗨️👁️‍🗨️◽☦️◽☦️🔲☦️♾️◼️♾️🔲◾◾™️▪️♾️☦️☦️♾️☦️▪️🛐💟🔲➿🕎🕉️🛐👁️‍🗨️➰🎼🛐➰🕉️✡️🎼🎼🕉️✡️☦️♾️▪️☦️🕉️▪️▪️🎼🕉️🎼🕉️▪️✡️🎼🕉️🎼🕉️✡️🎼🕉️✡️🎼✡️🕉️⚕️🕉️✝️🎼🕉️✡️🎼✡️🕉️🎼✡️🕉️🎼🕉️✡️🎼🕉️✡️✡️🎼🕉️🎼🕉️✡️✡️🎼🕉️🎼▪️🕉️✝️🕉️⚕️⚕️🔘♾️⚕️⚕️♾️⚕️🎼✡️🕉️⚕️🔘🕉️⚕️✝️🕉️🔘⚕️♾️⚕️♾️🔘🔘⚕️💟⚕️🕉️🔘⚕️✝️🕉️✡️🕉️⚕️⚕️✝️🕉️🕉️⚕️✡️🔘◼️♾️◼️💟🔘◼️◻️◼️💟🔘◼️♾️💟🔘◼️◼️◻️◻️®️◻️😆◼️🔘💟◻️®️®️®️😆◻️◻️®️◻️😆™️◾😆◾™️®️🔘◻️🔘◻️®️®️®️🔘◻️®️💟🔘◼️💟◼️✝️✝️◼️💟🔘💟◼️🔘®️◻️✝️◼️💟🕉️⚕️✡️🔼🆔〽️🔼🆔〽️🆔🔼〽️🔂🪯🛜🔂🪯🛜🪯🔼⛓️〽️⛓️🔼✴️🛜🔂🔼⛓️🔗🔼⛓️🔗🔼⛓️🔗🔼🔗⛓️🔼⛓️🔗🛐☸️⚛️🛐☯️☸️🕉️☸️☯️☯️➰☯️➰♾️✝️➰🔳➰✝️🔳✡️➿✡️♾️➿♾️✡️➿✡️♾️➿🛜☸️⚛️🕉️🕎🔯🕉️🔯🕎🕎🔯🕉️〽️🛐☸️🕎🪯🕉️✡️♾️🎼▪️♾️☦️✡️💟◼️💟🔘◼️🔘💟◼️🕎🎼🕉️🔂🪯🛜🔂🪯🛜🔼🆔〽️⚕️🆔🪯〽️👁️‍🗨️🎼⚕️🆔🪯〽️👁️‍🗨️🎼⚕️🆔🪯〽️⛓️〽️🔗〽️⛓️〽️🔗〽️⛓️〽️✴️〽️🔗〽️〽️🪯〽️🆔〽️🪯〽️🆔⛓️👁️‍🗨️⛓️👁️‍🗨️🔗👁️‍🗨️🔗👁️‍🗨️🎼⚕️🆔🪯〽️👁️‍🗨️💟☦️◼️®️◾◻️™️🔘▪️🔲◽➿➰🔲◽🔳☯️⚛️🔗✴️⛓️🔂🔼🛜〽️🪯🆔⚕️🎼👁️‍🗨️🕉️🛐🕎☸️🔯⚛️☯️➿➰✡️✝️♾️💟☦️◼️®️◾◻️™️🔘▪️🔲◽🔳⚕️
Comment from : @JohnRoberts-i4b

2025
Comment from : @ag___9905

love from India, sir
Comment from : @sriyaboora

All things are under ai control people belong to the good book
Comment from : @challahsmith3257

I've been studying machine learning models and got to neural networks, and it was a bit intimidating This excellent lecture took the "scary" right out of it
Comment from : @akirak1871

I dont know why but when i hearing about edicational things that are like 5 grades higher than me makes me feel scared
Comment from : @RykerCowne

Hi! I am medical doctor with little background on computing studies or mathematics but great interest in data and its use for medical research and patient's care I am now drafting a booklet on Machine Learning for health care workers with no previous coding background and found this video extremely clear and helpful Would you allow me to add a link to this video in the booklet?
Comment from : @mariasolandresMD

The picture at @3:35 looks like witch craft lol how do u keep tract of that much data
Comment from : @Sumpydumpert

Thank you too great video would they be building a quantum computer to be a single one of those dots to read internet transaction logs based on web page dynamics to filter and feed data across apps ?
Comment from : @Sumpydumpert

😎🤖
Comment from : @thesimplicitylifestyle

I just found your channel as a suggestion from a 3Blue1Brown video I subscribed instantly, easily explained, thanks
Comment from : @RolandoLopezNieto

I have this most pressing question of how deep neural networks and Ai is applied in chip designing I'm really curious to know from you Dr Steven Brunton Sir would u plz shed some light or your general view on my question
Comment from : @parikshithk8289

Amazing time spent to understand the Networks a little more
Comment from : @lightspeedlion

Nathan Kutz!? I took his class!
Comment from : @zfolwick

Zed Otherwise good
Comment from : @Kenbreg

True enough, but superficial No explanation No maths I didn't learn anything new
Comment from : @emjizone

One of the most effective and useful introductory lectures on neural networks you can attend It provides basic terminology and enables a good foundation for other lectures HIGHLY RECOMMENDED It would be helpful, Mr Bunton, to say a little bit more about Neurons Is a neuron strictly a LOGICAL function point in a process (my simple excel cell doing a logical function qualifies as a neuron with your definition), is it a PHYSICAL function point like a server, or is it both? Was there a reason you did not mention restricted Boltzmann motors? Thank you again, Sir, for the quality of this lecture
Comment from : @kennjank9335

It takes me a while to realize he writes with his left hand
Comment from : @elevenchen1084

This content is top-level! If you want to go further, I'd suggest a book that aligns well with this "From Bytes to Consciousness: A Comprehensive Guide to Artificial Intelligence" by Stuart Mills
Comment from : @bitsbard

Great explanation Thank u Sir
Comment from : @izainonline

7:45 Can it be combined with a Decision Tree? I think it would be a good idea, and I have found some research that has a similar idea
Comment from : @tsylpyf6od404

5:34 What about Spiking Recurrent Neural Networksbrgenerally SNN outperform RNN When it comes to problems that are changing times Although SNN He suffers from a weight problem, but isn't Spiking Recurrent Neural Networks It will be a better solution
Comment from : @tsylpyf6od404

I really appreciate this talk, thank you
Comment from : @FlowerPowered420

a fantastic overview thanks!!♥
Comment from : @neiltucker1355

Thanks for your explanation in the video have learned a lot Am doing research in speech emotion recognition Can you pls tell me the best Deep learning algorithms that will work?
Comment from : @radhikasece2374

brCan I use your mathematical apparatus, to investigate the physical processes of Metaphysics?? brI am looking for a mathematical apparatus capable of working with metaphysical phenomena, ie metamathematics!!
Comment from : @ko-prometheus

I am addicted to your series of lectures for the last three months your "welcome back" intro looks like a chorus to me thank you!
Comment from : @Savedbygrace952

How did you make this video editing? What software do you like to? I am very interested to know how you made this video
Comment from : @mahamatissa1711

THANK YOU
Comment from : @mahfuzulhaquenayeem8561

How come neurons in our brain have sigmoid activation functions?
Comment from : @alexwindmill7480

He Steve, thank you a lot for all your brilliant videos! One request on the topic, could you please cover how all this works with shift/rotation/scale of the image? Nobody on youtube covers this tricky part of the neuron networks used for image recognition I keep fingers crossed that you the one who could clarify this
Comment from : @doctorshadow2482

NEAT
Comment from : @nickmartin3647

Really clear Thanks for the vidéo !
Comment from : @sitrakaforler8696

I did not understand the architecture of neural networks I don't know how they work mathematically? Different shapes of them confused me Would you please clarify them?
Comment from : @najme9315

Dear Prof Brunten, Thanks for your nice lecture My field of study is mathematics You mentioned that there are different types of activation functions I saw in some lecture people said the aim of using activation function is nonlinear classification I don't know why these are called activation functions? i mean which property do they have? Can we create an arbitrary activation function or not?
Comment from : @najme9315

Love your videos and your book! Can't wait to start working through it actually!
Comment from : @goodlack9093

is there any channel like yours for Data Engineering topic
Comment from : @dickymr1878

Thank you so much for the video! The way you teach makes learning so much fun:) If you were born in ancient time, you alone would have shot the literacy rate by over 20
Comment from : @YASHSHARMA-bf2mm

We have to thank sir, Thank you Sir
Comment from : @mrdineshlee

I need to watch all the videos of this channel
Comment from : @hurricane31415

"a smiley face, I took this from Wikipedia" You know he's an academic when he cites EVERYTHING He cites a smiley face image
Comment from : @reallynotadatascientist

Dear Sir, would you mind advising which book will talk particularly on each of the architectures illustrated in the neural networks zoom? Thanks
Comment from : @hahe3598

once you get hold of the back propagation and how to do the chain rule derivatives, you understand that was not the goal! you merely opened the door, and this video is the way to your goal!
Comment from : @saysoy1

Very well explained Thank you
Comment from : @flaviudsi

Thanks, this was awesome
Comment from : @GewaltfreierFrieden

4:00 How come some of those don't have output nodes?
Comment from : @FederationStarShip

Professor I am a fan
Comment from : @humanyojk8930

what is your favourite neural network
Comment from : @realcirno1750

whats difference between recurrent and dynamic neural networks?
Comment from : @tkhankhoje39

Wait a second what?! Neurons in the brain have sigmoidal activation function?!! But in there we have spiking neurons, whose action potential can be modeled using Direc Delta function Am I missing something?
Comment from : @MLDawn

wait how does he draw in the air lol
Comment from : @realbrickbread

A question 3:20, what are f,g and h? I didn't see anything similar to these
Comment from : @hanyanglee9018

saas vs cloud public ont la meme fonctionnalité brje vous remercie de votre réponse
Comment from : @PTAH612

Thanks, Sir !
Comment from : @MrFischvogel

Thank you is all I can say but it doesn't feel like enough for this
Comment from : @nex4618

Thank you very much for this extraordinary way of teaching
Comment from : @karemabuowda2695

Oh wow I've been educated by your channel for a while now but did not realise you have published a textbook until your remark Only A$80 here in Aus Done! purchased
Comment from : @BenHutchison

Why is the topology not learned by an evolution algorithm and why is there not a structured hierarchical topology? (eg, different NN sub-topologies that are designed for specific parts that interact with others) Also, why are lunatics able to pay scientists to design AI to ruin humanity? Do you know the current state of the art AI is being used to extract trillions from the stock market and in to the pockets of the elites? Do you think the rich greedy bastards would just leave this technology alone?
Comment from : @jsmdnq

so many tons of tons
Comment from : @valentinofarris6124

You got a pretty MOUTH
Comment from : @brandonlee9528

amazing
Comment from : @7DYNAMIN

Finally, now I know what CaryKneesHurt is actually rambling on about!
Comment from : @okboing

SUBSCRIBEDDDDDD You are a star
Comment from : @yaminchoudhury8732

My prime struggle with NNs is what do the hidden layers do exactly
Comment from : @yugen3968

Thank you for this beautiful explanation I really enjoy it
Comment from : @aminnima6145

Subbed TY
Comment from : @ccdavis94303

Hey i know it's been a few years and it's an otherwise great video but you just seemed to imply "tanh" as an alternative name for sigmoid, which is a bit incorrect Only stating this since it's valuable information for learners to know how these two are similar (in shape) but very different functions Sigmoid goes from 0 to 1 but hyperbolic tangent goes from -1 to 1 which might not seem much of a difference but it's substantially different when you have architectures like LSTMs Referring to 1:10
Comment from : @rajdeepbiswas8912

Nice video
Comment from : @dogeofvenice5624

Thank you Harrison Wells
Comment from : @fisslimen

Beautiful
Comment from : @juliocardenas4485

Great content for existing developers Wow Incredible To say the least I am speechless You didn’t waste my time and I appreciate that!!
Comment from : @tottiegod8021

am I the only one that searched for this?
Comment from : @jonathanclark7444

Amazing Thank you :)
Comment from : @jeewonkyrapark9153

beautiful! thanks
Comment from : @Didanihaaaa

Thx
Comment from : @brendawilliams8062

The space of bullet points on the first slide triggers
Comment from : @SaltyRamen

Sir what is DCIGN
Comment from : @bcciindia1947

I love this man You are my role model
Comment from : @namhyeongtaek4653

Finally a good presentation
Comment from : @DanWilan

YouTube read my mind this was exactly what I was curious about
Comment from : @vinster9165

Nice
Comment from : @jackerylel

Sir your deep learning videos are the only ones on Youtube I take seriously
Comment from : @XecutionStyle

finally, i found this
Comment from : @assulaeman6174

What software are u using for creating these visualizations?
Comment from : @frankd1156

I believe the brain is a facilitator consciousness isn't a sell out hahahahah bypass the brain my new studyleads me brInto the woods for GOD PRIME CREATOR
Comment from : @jaimieb1177

I like the way of explaining by projecting on glass boardvery very nice
Comment from : @youcanlearnallthethingstec1176

trying to create neural network through manual arrangements is fool's errand What is needed is Genetic Algorithm which can generate a best neural net configuration that can learn the task bestbrusually the process goes like thisbrdata -> some neural net -> modelbrbut the better approach isbrdata -> genetic algo -> neural netbrdata -> neural net -> modelbrbrin essence you are not just adjusting weights, but also topology with data, surely changes in topology need to slowerbrbrwhat factors can we control in a neuronbr- input power for it turn on (threshold, usually the only thing that's controlled)br- time it stays on (active period)br- time it needs to recharge (cool off period)br- time it takes from on trigger to output on (delay period)brbranother flaw in topology is it's always forward facing, real brain is more like a graph than layers
Comment from : @techsinpower4773

loved it
Comment from : @adammendoza7615

?
Comment from : @mingzhao3477

simply great, thanks for this intro video
Comment from : @userou-ig1ze

Please can you help me with my MA research project titled Time-Series Deep-Learning Classifier for Human Activity Recognition Based On Smartphone Built-in Sensors Using matlab
Comment from : @ميكاساالعبيدي