Open in app

Sign In

Write

Sign In

Andrej Karpathy
Andrej Karpathy

47K Followers

Home

About

Nov 11, 2017

Software 2.0

I sometimes see people refer to neural networks as just “another tool in your machine learning toolbox”. They have some pros and cons, they work here or there, and sometimes you can use them to win Kaggle competitions. Unfortunately, this interpretation completely misses the forest for the trees. Neural networks…

Machine Learning

9 min read

Software 2.0
Software 2.0
Machine Learning

9 min read


May 31, 2017

AlphaGo, in context

Update Oct 18, 2017: AlphaGo Zero was announced. This post refers to the previous version. 95% of it still applies. I had a chance to talk to several people about the recent AlphaGo matches with Ke Jie and others. In particular, most of the coverage was a mix of popular…

Machine Learning

5 min read

AlphaGo, in context
AlphaGo, in context
Machine Learning

5 min read


May 24, 2017

ICML accepted papers institution stats

The accepted papers at ICML have been published. ICML is a top Machine Learning conference, and one of the most relevant to Deep Learning, although NIPS has a longer DL tradition and ICLR, being more focused, has a much higher DL density. Most mentioned institutions I thought it would be fun to compute…

Machine Learning

2 min read

Machine Learning

2 min read


Apr 7, 2017

A Peek at Trends in Machine Learning

Have you looked at Google Trends? It’s pretty cool — you enter some keywords and see how Google Searches of that term vary through time. I thought — hey, I happen to have this arxiv-sanity database of 28,303 (arxiv) Machine Learning papers over the last 5 years, so why not…

Machine Learning

6 min read

A Peek at Trends in Machine Learning
A Peek at Trends in Machine Learning
Machine Learning

6 min read


Mar 14, 2017

ICLR 2017 vs arxiv-sanity

I thought it would be fun to cross-reference the ICLR 2017 (a popular Deep Learning conference) decisions (which fall into 4 categories: oral, poster, workshop, reject) with the number of times each paper was added to someone’s library on arxiv-sanity. ICLR 2017 decision making involves a number of area chairs…

Machine Learning

11 min read

ICLR 2017 vs arxiv-sanity
ICLR 2017 vs arxiv-sanity
Machine Learning

11 min read


Jan 17, 2017

Virtual Reality: still not quite there, again.

The first time I tried out Virtual Reality was a while ago — somewhere in the late 1990's. I was quite young so my memory is a bit hazy, but I remember a research-lab-like room full of hardware, wires, and in the middle a large chair with a big helmet…

Virtual Reality

11 min read

Virtual Reality: still not quite there, again.
Virtual Reality: still not quite there, again.
Virtual Reality

11 min read


Dec 19, 2016

Yes you should understand backprop

When we offered CS231n (Deep Learning class) at Stanford, we intentionally designed the programming assignments to include explicit calculations involved in backpropagation on the lowest level. The students had to implement the forward and the backward pass of each layer in raw numpy. …

Machine Learning

7 min read

Yes you should understand backprop
Yes you should understand backprop
Machine Learning

7 min read


Nov 15, 2015

CS183c Assignment #3

The last few weeks we heard from several excellent guests, including Selina Tobaccowala from Survey Monkey, Patrick Collison from Stripe, Nirav Tolia from Nextdoor, Shishir Mehrotra from Google, and Elizabeth Holmes from Theranos. The topic of discussion was scaling beyond the tribe phase to the Village/City phases of a company. …

Startup

4 min read

Startup

4 min read

Andrej Karpathy

Andrej Karpathy

47K Followers

I like to train deep neural nets on large datasets.

Following
  • Leon Palafox

    Leon Palafox

  • Pardis Noorzad

    Pardis Noorzad

  • Luke Hutchison

    Luke Hutchison

  • Eugenio Culurciello

    Eugenio Culurciello

  • Nicolas Pinto

    Nicolas Pinto

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech