@anderton_tim

machine learning for fun and profit (mostly fun).

 Bountiful, UT
asymptoticlabs.com
Joined October 2014
  • Tweets90
  • Following279
  • Followers30
5Media
Bro, if you were to find a job using y=mx+b, I am fairly certain you could double your income. No joke
This Post is from a suspended account. Learn more
5
4
94
Tim Anderton retweeted
Vala Afshar
@ValaAfshar20 Aug 2022
This is how we should teach physics and engineering principles in high school
147
3,673
188
19,863
All of linear algebra in one diagram:
60
1,174
91
6,183
I’m gonna write a book on stats one day, and there will be an entire chapter on not being such a rule based hard ass and knowing when to commit a statistical sin in the name of getting an approximate answer to a precise question
2
4
56
Gradient descent/ascent can be inefficient to find saddle point (Nash equilibrium) for min-max games, because of spiralling behaviour. en.wikipedia.org/wiki/Nash_e…
8
175
10
989
Tip #1: when building models with the Functional API (keras.io/guides/functional_a…), you can use an intermediate output as entry point to define a new Model. This is especially useful to create pairs of models where one includes preprocessing (e.g. for inference), and one does not.
5
12
2
132
I believe eigen fly I believe eigen touch the sky
56
985
127
7,413
The dumbest, most impotent idea of the 2010s and 2020s is the notion that you can fight disinformation with actual information. It's like fighting a forest fire by planting trees.
12
49
10
282
Wait, what
31
308
70
2,750
Really looking forward to this Boston cream Pi :)
Tim Anderton retweeted
Andrej Karpathy
@karpathy7 Feb 2021
Everyone is so obsessed with accelerating neural nets, so as a fun side project I've been building this breadboard 8bit neural net decelerator. It will crawl at best :D. (following along the excellent++ Ben Eater 8-bit computer eater.net/8bit/)
45
118
12
1,705
Tim Anderton retweeted
Peter Wang 🦋
@pwang30 Nov 2020
Just a reminder that there is no such thing as data, only frozen models. I’m not particularly encouraged by the models being frozen into these metrics.
Wolfie Christl@WolfieChristl24 Nov 2020
Esoteric metrics based on analyzing extensive data about employee activities has been mostly the domain of fringe software vendors. Now it's built into MS 365. A new feature to calculate 'productivity scores' turns Microsoft 365 into an full-fledged workplace surveillance tool:
1
2
6
Wanted: a group videoconference interface that includes a running "chess clock" indicating the proportion of the event time that each participant has talked.
7
21
3
131
Tim Anderton retweeted
Jesse Engel@jesseengel26 Nov 2019
Wouldn't it just be a lot more self explanatory is we called Transformers something like Key-Query Networks (KQNets)?
9
4
2
118
Tim Anderton retweeted
Francis Bach@BachFrancis4 Nov 2019
Nothing beats some polynomial magic to start the week, with a new blog post on Chebyshev polynomials. francisbach.com/chebyshev-po…
5
86
7
388
Tim Anderton retweeted
Lex Fridman
@lexfridman25 Sep 2019
New proposal for Turing Test in robotics: The Door Handle & Water Tub Test. The task is to achieve cat-level perception, reasoning, learning, manipulation, and dynamic planning under uncertainty.
37
339
27
2,121
Tim Anderton retweeted
hardmaru
@hardmaru25 Sep 2019
Using gradient descent for everything xitter.cf/danhett/status/1176116…
41
418
50
2,338
Tim Anderton retweeted
Brian P. Hogan
@bphogan15 Sep 2019
I’ve hired a few people in my time. I’ve never been disappointed by hiring someone who is less technical but is a great human who cares for others. I can teach tech pretty easily. But boy have I seen people who are strong technical people with toxic attitudes destroy a team.
505
11,571
939
56,149
Wow, what a plot twist in the abstract! (@sandsubramanian et al)
44
1,066
184
3,301
Tim Anderton retweeted
Hiten Shah
@hnshah9 Sep 2019
Happy Monday! Inspiration for the week. Sometimes it takes a few attempts to get through a seemingly impossible barrier. xitter.cf/nosabesnadajon/status/…
250
4,542
480
24,387
Load more