This video will change your mind about Neural Networks - by Daniel Boctor
via Invidious:
https://inv.nadeko.net/watch?v=eCU2vQs0Q6s
(or YT: https://www.youtube.com/watch?v=eCU2vQs0Q6s)
Brilliant explainer video with great visualizations on how neural networks work.
#NeuralNetworks #NeuralNets #AI #ArtificialIntelligence #Video #Statistics
To try everything Brilliant has to offer โfreeโ for a full 30 days, visit ๐ https://brilliant.org/DanielBoctor/. You'll also get 20% off an annual premium subscription! In this video, we take a deep dive into the inner workings of neural networks, one of the most influential, powerful, and widely used machine learning models within the field of artificial intelligence (AI), and computer science as a whole. Variants of neural networks are what power services such as ChatGPT by OpenAI, GitHub copilot, and DeepSeek. We demystify these models, building a mechanical understanding of what they really are, how the function, and how they learn. JOIN THE DISCORD! ๐ https://discord.gg/WYqqp7DXbm 0:00 โ Intro 0:36 - Single node network 2:34 โ Multi node network 6:03 โ Architecture 6:54 - Parameters 9:28 - Activation functions 11:27 - Impact of Activation functions 12:08 - Logistic regression 15:32 - Learning 19:15 - Closing remarks MUSIC CREDITS: Music by Vincent Rubinetti Download the music on Bandcamp: https://vincerubinetti.bandcamp.com Stream the music on Spotify: https://open.spotify.com/artist/2SRhEEt2tlDQWxzwfUo9Dl LEMMiNO - Firecracker https://www.youtube.com/watch?v=ulfoU2MziOc CC BY-SA 4.0 LEMMiNO - Nocturnal https://www.youtube.com/watch?v=epmoV2HRs9U CC BY-SA 4.0 LEMMiNO - Siberian https://www.youtube.com/watch?v=5py6E6yo7wk CC BY-SA 4.0 LEMMiNO - Encounters https://www.youtube.com/watch?v=xdwWCl_5x2s CC BY-SA 4.0 #programming #software #softwareengineering #computerscience #code #hacking #hack #cybersecurity #exploit #tracking #softwareengineer #vulnerability #pentesting #privacy #spyware #malware #cyber #cyberattack #security #bug #backdoor #hacked #leak #chatbot #AI #LLM #chatgpt #openai #windows #neuralnetwork #informationsecurity #trending #machinelearning #deeplearning #machinelearning #chatGPT #deepseek #copilot #tech #computerscience #artificialintelligence #microsoft #languagemodel #transformer
๐ Excited to announce my 5th course, Network Algorithms and Approximations! ๐ Explore NP-complete problems (Set Cover, Unique Coverage, etc.), approximation techniques, and applications in data science, neural nets, & network optimization.
๐บ First lecture: https://youtu.be/Tnm-8xieqB4
๐ฅ Weekly uploads: Wednesdays at 7 PM EDT. Playlist: https://youtube.com/playlist?list=PLx7SjCaKZzEIeJxOlTuXveAE5eY7WOYB9
Plus, all 4 previous courses (Game Theory, Algorithms, Lower Bounds, Data Science) are online! ๐ https://youtube.com/@hajiaghayi
#NetworkDesign #Optimization #NPComplete #Algorithms #DataScience #NeuralNets
@kellogh It's an advanced pattern recognition machine, nothing more.
And yes, we don't really know what's happening within #LLMs #NeuralNets - and this makes it worse!
AIs are intuitive, not thinking machines, which is not enough to produce code that is high quality and can be trusted:
Very interesting thread:
https://floss.social/@janriemer/109479731267566070
Also, there is _so much more_:
- I want an #AI, that _expresses uncertainty_ with line number range
- asks questions back, not just spit out bs!
@AstraKernel@infosec.exchange @lx@tooting.ch Well, I guess the prompt was something like "Produce a buffer overflow in Rust". As #AI's are just stupid statistical models, they think: Hey, I've seen _many_ buffer overflow examples in C and "buffer overflow" mentioned with C, so let's convert that to Rust - et voilรก. It doesn't _understand_ that Rust is a safe language. We should not expect reasoning or intelligence from an AI. It is pattern matching, nothing more. #ArtificialIntelligence #PatternMatching #NoReasoning
Wait, #LLMs or #NeuralNets can't reason!? This is so surprising! How could that happen!? This is unbelievable! I'm in shock!
But they surely have feelings, right...right!?
Does anyone know the URL for the "observatory" website (I think that's what they called it) where one of the AI/DNN labs had analysed various machine vision models and built a map of all of the nodes.
You could click on each node and see the images (and sometimes text) that triggered it, and also images that were generated when they excited that node while clamping others (like Deep Dreams)
I can't remember who it was and can't find it.
The Artificial Intelligence Papers
Original Research Papers With Tutorial Commentaries
https://jamesstone.sites.sheffield.ac.uk/books/theaipapers
Friend and colleague Jim Stone has a new book, with a "no mercy" cover and bomber content for understanding the technical foundations of the current AI moment
About this book Modern artificial intelligence (AI) is built upon a relatively small number of foundational research papers, which have been collected and republished in this unique 350-page book. The first chapter provides a summary of the historical roots of AI, and subsequent chapters trace its
CLIRSPEC
Jan 
Dirk Van den Poel
Mohammad Hajiaghayi
sneumann
Dan Stowell
IBBoard
Tom Stafford