P01YM47H @p01ym47h-blog - Tumblr Blog

Phenomenal explanation of bayesian v. frequentists techniques using Chutes and Ladders.

#markov chains #monte carlo simulations #stochastic processes #chutes and ladders #statistics

Rock solid mathematical and technical overview of audio signal processing, fingerprinting, and recognition.

#signal processing #computer science #pattern recognition #programming #fourier transform

Title says it all. A simple comparison of L1 and L2 as the loss function and also as regularization (aka "ridge" and "lasso").

#machine learning #computer science #statistics

"e has always bugged me". I completely agree. My teachers always gave me circular definitions based on the natural log. I used and abused e on the daily without truly understanding its derivation. No more!

#math #e #exponential growth

alt text: Even the identity matrix doesn't work normally

#xkcd

Congrats to Sam Altman on taking over the Y-Combinator reins from PG. No pressure bro. In this blog post Sam gives a great, simplistic assessment of the current state of AI.

Yesterday at lunch a friend asked me what tech trend he should pay attention to but was probably ignoring. Without thinking much I said âartificial intelligenceâ, but having thought about that a...

Quick aside: there are a lot of haters out there who bitch about AI not truly replicating human intelligence. Yes. Of course. Did you expect it to? I wonder if people bitched equally when we first developed submarines. A whiny noise from the back of the room complaining, "yeah, but it doesn't swim like fish!" (to take a page from Dijkstra). And you're right, planes are nothing like birds. Who cares? Yes, completely reverse engineering a bird, like the brain, would bring humanity wonderful new insights and advance technology significantly. We will adjust our hardware and software accordingly when that day comes. But no one is complaining when they're hauling ass at half the speed of sound on a thousand ton, wifi-equipped, 200 person, flying luxury skyscraper that it just isn't similar enough to birds, are they? Look AI pessimists, machine learning algorithms are not based on the human brain! There are a lot of fancy ways of fitting a function to large quantities of data. That vague explanation is the essence of present-day machine learning. One day we will replicate the hardware and algorithms that makeup the human brain, the most complex thing that we know of in the universe. Until then you're stuck living in a world filled with shitty, non-human-like AI that doesn't fall in line with your perceived notion of intelligence. Your glass will always be half empty.

#machine learning #computer science #sam altman #ai

A fantastic, compact cheat sheet, great for reference and review.

#data science #data mining #statistics #machine learning #math #probability

#data visualization #twitter #sotu #politics #programming

In order to bear results, philosophical questions need to be formulated or broken down in such a way that they can be worked upon mathematically and computationally. The philosophy community has known this for some time. To me, a philosophy novice, this is new and pleasing.

A discussion a year ago with my older brother weighing the importance of philosophy, a quick read of the wonderful, and highly accessible Logicomix (thank you Thorup), and the post above, an interview with Scott Aaronson, helped me realize my perception of philosophy was flawed. I believed the entire field consisted of Hume, Kant, Locke, Mill, Aristotle, Plato, and other premodern philosophers. When in reality, mathematicians and logicians of the 19th and 20th centuries drove philosophy toward analytical rigor. Frege, Cantor, Russel, Gödel, Von Neumann, Turing, and others, pushed philosophy toward provability. Without mathematical rigor, philosophical questions remain intractable. And even if mathematics, at its axiomatic core, is a human defined, incomplete system, moving philosophy towards a rigorous, mathematical framework is still beneficial. But maybe I need to be slapped a little harder in the face by Gödel's incompleteness.

It will be exciting to watch the progress of computational learning theory in coming years. Just how far can we push machine learning?

#machine learning #computer science #scott aaronson #intelligence #computational learning theory #philosophy #math

#haskell #dijkstra #cs #programming #computer science #functional programming

Clean delivery of population information across time. If only they included application level interactivity with these charts as well.

#npr #visualiazation #gifs #population

kingjamesprogramming

Markov Chain Trained on the King James Bible and Structure and Interpretation of Computer Programs

p01ym47h-blog

26:27 And if ye shall at all turn from following me, that they are both symbols and the symbols are 1, 2, 4, 8, 16, 32, ….

Sci-fi Future, here we come.

#bci #brain computer interface #computer science #brains #technology

Trending Blogs

Recently Viewed Blogs

P01YM47H