Главная
Study mode:
on
1
Introduction
2
Example of an experiment
3
Example of charming humans
4
Limited information
5
Experiment
6
Cookies
7
Surface appearances
8
Puns
9
Neural net jokes
10
April Fools jokes
11
Limited memories
12
Long memories
13
Unfair situation
14
Pony classification
15
Application image recognition
16
Fun to enjoy
17
Problem is too broad
18
Recipe for success
19
Another example
20
For example
21
It made some mistakes
22
Several in fact
23
Consistent
24
Clocks
25
Sheep
26
Wool
27
surrealism
28
sheep surrealism
29
spooky clocks
30
training data
31
boring pictures
32
pizza girl
33
image recognition algorithms
34
adversarial attacks
35
Skynet
36
Knitting example
37
Challenges
38
Knitting
39
Knitting without debugging
40
Tiny baby whales Soto
41
The knitters liked it
42
Perfection is always a bad thing
43
Take home message
Description:
Explore the humorous side of machine learning failures in this 39-minute conference talk from Strange Loop. Discover how common algorithmic mistakes can lead to unexpectedly entertaining results, as presented by Janelle Shane from AIweirdness.com. Delve into examples of overfitting, noisy data, and overly general problems, learning how these issues can be deliberately used for creative purposes. Examine fascinating case studies, including cookie experiments, pun generation, neural net jokes, and image recognition mishaps. Gain insights into the challenges of knitting algorithms, adversarial attacks, and the importance of imperfection in AI development. Leave with a fresh perspective on embracing and learning from machine learning errors in both serious applications and artistic endeavors.

Machine Learning Failures - For Art

Strange Loop Conference
Add to list
0:00 / 0:00