Video wird geladen...
Video konnte nicht geladen werden
Timelapse #171 (14.5 hrs) - Contract work - continue testing D-Spark and the Laguna model drastically increased throughput of my kernel RL engine with D-Spark to hold up to high concurrencies and remove some bottlenecks with compilation time - working on kernel bench multi-GPU and kernel bench mini at... show more
27,408 Aufrufe • vor 2 Monaten •via X (Twitter)
21 Kommentare
idk how do you work from your bedroom, I kinda need an office which is not in my apartment
low bandwidth between waking up and kicking off more runs
@mihirneal how much meter squared is this
@mihirneal havent measured
Are you sure this isn’t COVID level isolation ? Timelapses are awesome and the setup looks cozy sometimes, but bro!
pretty close to covid level but im enjoying it
You don't have a window open, right? Doesn't CO2 build up if you stay that long without any air circulation?
Imagine what it will feel like
Asking again what chair do you have? I need a new one that will support me for hours.
cant remember. some knock off herman miller type
🐐🐐🐐🐐
this guy doesn't miss
Please keep the lights on for your eyes my man :’)
fun
new angle is epic
nice to know im not the only one living the grind
keep going Elliot
This is how we build a Typescript TODO app with the current stacks. 😂
Dope Timelapse Elliot.
I did 9h today, gonna do 5 more
Set yourself a limit - you can't work like this for months - seriously mate draw a line in the sand, name the date then take a two week break from the 14hr days.
![SVM by hand ✍️ ~ 19 steps walkthrough below (Linear vs RBF) Support Vector Machines reigned supreme in machine learning before the deep learning revolution. An SVM predicts with dot products, the same matrix multiplication every model uses. What it does not do is train by backpropagation: it is fitted by convex optimization, so there is no matrix-multiplication backward pass for a GPU to accelerate. I drew and calculated two SVMs by hand: a linear one (top) and an RBF one (bottom), classifying the same two test vectors. Goal: turn six training vectors and their learned coefficients into a prediction, and see what changing the kernel actually changes. = 1. Given = Six training vectors, their labels, and the coefficients and bias already learned. A coefficient of zero means that vector is not a support vector: too far from the boundary to matter. = 2. Linear kernel, test vector 1 = Let us take the dot product of the test vector with every training vector. The dot product stands in for cosine similarity, and the column of results is the first column of the kernel matrix K. = 3. Linear kernel, test vector 2 = We do the same for the second, and K is complete. = 4. Signed weights = Let us multiply each coefficient by its label. The second training vector drops out here, because its coefficient is 0. = 5. Weighted combination = We multiply the signed weights through K and add the bias b. The result is a signed distance to the decision boundary: 17 and 5. = 6. Classify = Let us take the sign. Both are positive. = 7 to 11. RBF kernel, test vector 1 = Now the same picture with a different kernel, in five moves: square the differences, sum them, take the square root for the L2 distance, multiply by minus gamma, and raise e to that power. The negation is what turns a distance into a similarity, and gamma controls how far a single training vector's influence reaches. = 12 to 16. RBF kernel, test vector 2 = We repeat all five. The numbers change, the moves do not. = 17 to 19. Decision boundary, again = Signed weights, weighted combination, sign. Identical arithmetic to steps 4 through 6, on a K that was built a completely different way. The outputs: Linear K, first column = [13, 25, 12, 15, 19, 27] Linear decision values = 17 and 5, both positive RBF decision values = -2 and 1, so negative and positive The takeaway: the kernel is the only thing that changed, and it changed the answer. The linear SVM calls both test vectors positive; the RBF one splits them. Everything after the kernel matrix, the signed weights and the weighted combination and the sign, is the same page of arithmetic twice. 💾 Save this post!](https://image.24vids.com/tw-2080658072842703031/ext_tw_video_thumb/2080658053083394048/pu/img/Lrl4Xyr6GSkbbbrN.jpg)
