With chants of U-S-A going on the first tee, JT and Jackson pump the crowd up to get even louder.
They take on Min Woo Lee and Sungjae Im in fourballs this morning.
These 94 lines of code are everything that is needed to train a neural network. Everything else is just efficiency.
This is my earlier project Micrograd. It implements a scalar-valued auto-grad engine. You start with some numbers at the leafs (usually the input data and the neural network parameters), build up a computational graph with operations like + and * that mix them, and the graph ends with a single value at the very end (the loss). You then go backwards through the graph applying chain rule at each node to calculate the gradients. The gradients tell you how to nudge your parameters to decrease the loss (and hence improve your network).
Sometimes when things get too complicated, I come back to this code and just breathe a little. But ok ok you also do have to know what the computational graph should be (e.g. MLP -> Transformer), what the loss function should be (e.g. autoregressive/diffusion), how to best use the gradients for a parameter update (e.g. SGD -> AdamW) etc etc. But it is the core of what is mostly happening.
The 1986 paper from Rumelhart, Hinton, Williams that popularized and used this algorithm (backpropagation) for training neural nets:
https://t.co/f52IcDNitR
micrograd on Github: https://t.co/GaTd16jRnB
and my (now somewhat old) YouTube video where I very slowly build and explain:
https://t.co/EPGG6kd5Yz
How do financial institutions actually decide which blockchain to build on?
Mastercard and the Sei Development Foundation interviewed 40+ leaders across payments, compliance, and blockchain infrastructure to find out.
This is what institutions actually prioritize.
What drives a diffusion model's creativity (i.e., its ability to generate novel data rather than memorize)? Today we show this is a mathematical consequence of neural network regularization causing score smoothing and interpolation. Read the blog to learn more: https://t.co/menk2a3Xy6
Tesla accelerated the electric vehicle market by selling over 9 million battery-powered cars and trucks. Now Elon Musk’s automaker is pivoting to humanoid robots and self-driving taxis. Up next: he’s looking to build AI data centers in orbit via his rocket company SpaceX, which recently committed at least $100 billion to building a spaceport in Louisiana.
His contributions added him to the list of #Forbes250 Builders: https://t.co/d0r815IQex
📸: Patrick Pleul via Getty Images
1/ Though painful short term for the crypto industry, the #binance fiasco will push the space towards transparent decentralized protocols.
But it won't be easy. Users love Binance for the product they've built.
A thread on how @HyperliquidX is answering the call 🧵
"Our results reveal that whenever handwriting movements are included as a learning strategy, more of the brain gets stimulated, resulting in the formation of more complex neural network connectivity...typewriting do[es] not activate...networks the same way that handwriting does."
Grok Bot has just officially launched in @Tesla vehicles.
I got early access a couple weeks ago. You can order stuff on online (such as Amazon), manage your email, calendar, finances, or other tasks through Grok @Bot using just your voice in your Tesla.
There is no separate app, everything just lives within the existing Grok Voice interface in your Tesla (as shown in my Model Y below).
One good use case for Grok Bot in your Tesla: You get in, tell Grok Bot to order coffee at a location of your choice, and while your Tesla drives you to the coffee shop using FSD (Supervised), Grok places the order so it’s ready when you arrive.
Grok Bot in Tesla vehicles is currently only available to SuperGrok Heavy users, but will expand to more owners later. Connectors are available to all users.
Jascha Sohl-Dickstein has an amazing blog post showing that the boundary between hyperparameter settings where neural network training succeeds and fails has a fractal structure.
The visualizations are mesmerizing.
https://t.co/j6xb3kNXzl
Did you know that an artificial neural network is designed to mimic the brain?
Inspired by biological neurons in the brain, artificial neural networks are large collections of “neurons”, or nodes, connected by “synapses”, or weighted couplings, which are trained to perform certain tasks. An artificial neural network processes information using its entire network structure. The inspiration initially came from the desire to understand how the brain works.
Learn more about this year’s physics prize awarded for work on artificial neural networks: https://t.co/QuIdxRvuEP
#NobelPrize
🚨 BREAKING: President Trump announces he will be appointing a HIGH IQ "AI CZAR" and launches the "AI FORCE"
Trump says we will UNLEASH AI and that the propaganda will fail
All of this will be geared towards not only BUSTING anti-AI hoaxes but keeping America number one. LET'S GO! 🔥
"I am forming the AI Force, much like I did Space Force, which has been a tremendous SUCCESS, in my First Term. To that end, I will be announcing, in the near future, the AI “Czar” — Only High I.Q. individuals need apply! AI is the next Industrial Revolution, or Internet, but will be even larger and more impactful, possibly as much as 25% of our Country’s GDP. We are leading China, and the rest of the World, and I intend to keep it that way!"
"Over the years, there have been many Hoaxes, all generated by the Radical Left Dumocrats, for purposes of destroying our Country. RUSSIA, RUSSIA, RUSSIA, UKRAINE, UKRAINE, UKRAINE, Global Warming, Impeachment Hoax 1, Impeachment Hoax 2..."
"Now, the decimation, or destruction, of AI, commonly known as Artificial Intelligence — And I, as President of the United States, will not stand by and let this happen."
"It all began with an attack on our Data Centers, until people realized how wealthy and prestigious they were for the Communities in which they were built."
"Higher Salaries, Lower Taxes, and Safer Streets, was the result, and the crazed Data Center attack has largely failed, so now, in much the same way as they changed the term “Global Warming” to “Climate Change,” in that it covers a much larger “territory” of doubt, they are going straight at AI. We will not in any way hinder or stifle the Growth of this incredible Industry."
"Rather, we will cherish it, help it, and watch over it, as it grows! However, we will also be looking for BAD, and we can do that, very easily, with our already existing Criminal and Civil Justice System."