Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Spiking Neural Network from scratch achieves 8% accuracy. no backpropagation or SGD I created a genetic hyper parameter optimizer and it now, on average, can get 8% accuracy which is ~3% above chance Link to source code with a detailed video and markdown explanations in comment it also usually...

225,484 Aufrufe • vor 11 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

As many of you know, for the last five months I've been working full-time on my next big thing. The challenge was to invent something new and implement it entirely using LLMs for writing code. The first stage of the project is now complete: the web application, which I called is now online and accepting users. You can see a short demo in the video. 100% of the code of the app was generated by LLMs (mostly Gemini and Claude, maybe 10% of ChatGPT). I haven't written a single line of code. The tech stack is TypeScript, React, and Supabase/Postgres which was (and still is) fully new to me. During these five months, I implemented from scratch three versions of the software. It started as a Markdown editor to help me with my book writing and ended up as an AI-assisted reading and self-learning platform. What makes ChapterPal unique is a novel reading experience where the user can use the keyboard keys to reveal or "unreveal" the content and ask questions at any moment. (Mouse wheel, touchpad, smartphone screen, and voice input are also supported.) The LLM receives the entire content of the chapter and tries to answer questions based on the chapter's content, which reduces the chance of hallucination to the minimum. (Though not to 0%, of course, but near it.) This way of content consumption is known as **active reading,** a strategy for engaging with a text to improve comprehension and retention by consciously interacting with the material. The goal is to move beyond passive reading to a deeper understanding of the text and to remember key information more effectively. The registration on ChapterPal is via the waiting list. This is to avoid unexpected load spikes and cloud charges. Usually, it takes less than 24 hours for me to activate a user. Give it a try and let me know what you think. The next stage is finishing the content ingestion pipeline, which will automatically convert high-quality content from sources like HTML, PDF, and LaTeX into Markdown. Obviously, only those pieces whose licenses allow creating copies. ChapterPal has its own collection of textbooks and articles on AI, machine learning, and data science topics. If you don't find a piece of content you would like to read in ChapterPal's collection, a Chrome extension, ChapterPal Uploader, allows you to upload any PDF or HTML page to ChapterPal in one click. The content is only available for you to read to avoid the possibility of copyright infringement. I hope you enjoy using it as much as I enjoy building it.

BURKOV

81,258 Aufrufe • vor 10 Monaten

Former Meta Chief AI Scientist Yann LeCun on the three paradigms of machine learning — and why the third is what made ChatGPT possible: Here's each one, and where it breaks. First, supervised learning. You tell the machine the answer. "You show it a picture, let's say of a table, and you tell it this is a table. So it's supervised because you tell it what the correct answer is." Get it wrong, and the machine rewrites itself: "The system computes its output, and if it says something else than table, then it's going to adjust its parameters, its internal structure, so that the output it produces gets closer to the output you want." Repeat at scale and something more than memorisation appears: "Eventually the system will find a way to recognize every image you trained it on, but also images it's never seen that are similar to the one you train it on. This is called a generalization ability." The limit: a human has to supply every single answer. That doesn't scale to the size of the internet. Second, reinforcement learning. You don't give the answer, only a verdict. "You don't tell the system what the correct answer is. You only tell it whether the answer it produced was good or bad." Learning to ride a bike, essentially: "You try to ride a bike and you don't know how to ride the bike and after a while you fall. So you know you did something bad and so you change your strategy a little bit. And eventually you learn how to ride a bike." For years the field assumed this was the closest thing to how animals actually learn. Yann LeCun's verdict: "Now it turns out reinforcement learning is extremely inefficient." It dominates wherever failure is free: "It works really well if you want to train a system to play chess or play go or poker, because you can have the system play millions and millions of games against itself and basically fine-tune itself. But it doesn't really work in the real world." The limit, in one image: "If you want to train a car to drive itself, you're not going to do it with reinforcement learning. It's going to crash thousands of times." On robotics he's careful rather than dismissive: "Reinforcement learning can be part of the solution, but it's not the complete answer. It's not sufficient." Third, self-supervised learning. You tell the machine nothing at all. "And this is what has enabled the recent progress in natural language understanding and chatbots." The strange part is that you stop asking for a task: "You don't train the system to accomplish any particular task. You just train it to basically capture the structure..." The method is deliberate sabotage: "You take a piece of text, you corrupt it in some way, by for example removing some words, and then you train a big neural net to predict the words that are missing." And one narrow version of that trick runs every chatbot on Earth: "A special case of this is that you take a piece of text and the last word in that text is not visible, and so you train the system to predict the last word in that text — and this is the way large language models are trained on." So why did the third one win? Supervised learning needs a human. Reinforcement learning needs a crash. Self-supervised learning needs neither — because the missing word and the correct answer are the same thing. The data grades itself.

Big Brain AI

49,293 Aufrufe • vor 1 Monat

"Spike protein was designed as a bioweapon...this entire pandemic was to reduce life expectancy...the United Nations has been clear about its intentions to reduce the world's population. So they created a virus to create a need for a vaccine, both of which had this bioweapon."** Canadian physician Dr. Charles Hoffe describes during a recent World Council for Health (World Council for Health (WCH)) discussion how he believes that the now-infamous "spike protein" was designed as a bioweapon. Hoffe says that he believes both the COVID-19 "pandemic" and the injections released to—ostensibly—immunize people were both created with the intention of "reducing the world's population." "I think the most critical thing to understand is that spike protein was designed as a bioweapon. I mean, it's now fairly clear that this entire pandemic was to reduce life expectancy," Hoffe says. "The United Nations has been quite clear about its intentions to reduce the world's population, and so they created a virus to create a need for a vaccine, both of which had this bioweapon, which is the spike protein." Hoffe goes on to say: "For those that managed to resist being forced into having the shots or were not coerced into it through fear, they got the spike protein from COVID infections or from shedding. So basically, we have all been spiked. And, of course, those who got the shots became spike protein factories and they got more than anyone else, but we have all been poisoned. "So there are many people who didn't have the shots who are noticing changes in their health. And I think, as a family doctor, what I'm seeing the most is recurrent infections and mostly viral infections, but some people with recurrent bacterial infections as well. And this is, just as doctor Villa mentioned, from this assault on our immune system. And, of course, the cancers are part of that and the autoimmune problems are part of that. But I think the most critical thing is that we've all been spiked, and, therefore, we all need to take measures to deal with that." **While I agree the injections are bioweapons and the UN (and whoever else is in the global cabal) wants to depopulate Earth, I believe it is more likely the cause of COVID is a chemical weapon and not a virus.

Sense Receptor

25,892 Aufrufe • vor 1 Jahr