12.
Vladimir Haltakov
@haltakov
Mastering your Machine Learning Interview โ
I've summarized some great resources for you that will help you withโฆ twitter.com/i/web/status/1โฆ
I've summarized some great resources for you that will help you withโฆ twitter.com/i/web/status/1โฆ
13.
Vladimir Haltakov
@haltakov
Data labeling - how hard can it be?
Well, it is *very* hard to curate a dataset with high-quality ground trutโฆ twitter.com/i/web/status/1โฆ
Well, it is *very* hard to curate a dataset with high-quality ground trutโฆ twitter.com/i/web/status/1โฆ
14.
15.
16.
17.
18.
Vladimir Haltakov
@haltakov
Hey
if you want to learn more about Machine Learning
Follow me
I'll teach you!
if you want to learn more about Machine Learning
Follow me
I'll teach you!
Vladimir Haltakov
@haltakov
There are two problems with ROC curves
They don't work for imbalanced datasets
They don't work for object deteโฆ twitter.com/i/web/status/1โฆ
They don't work for imbalanced datasets
They don't work for object deteโฆ twitter.com/i/web/status/1โฆ
Vladimir Haltakov
@haltakov
How to evaluate your ML model?
Your accuracy is 97%, so this is pretty good, right? Right? No!
Just looking aโฆ twitter.com/i/web/status/1โฆ
Your accuracy is 97%, so this is pretty good, right? Right? No!
Just looking aโฆ twitter.com/i/web/status/1โฆ
Vladimir Haltakov
@haltakov
Can the AI Wolf catch the Sheep ?
This is a simple game created by students in China. The goal is to train theโฆ twitter.com/i/web/status/1โฆ
This is a simple game created by students in China. The goal is to train theโฆ twitter.com/i/web/status/1โฆ
Vladimir Haltakov
@haltakov
AI Job Interviews - another good example of bias in ML
Two journalists tested some AI tools for assessing jobโฆ twitter.com/i/web/status/1โฆ
Two journalists tested some AI tools for assessing jobโฆ twitter.com/i/web/status/1โฆ
19.
20.
21.
22.
Vladimir Haltakov
@haltakov
Machine learning jargon explained โ
What are ๐ฝ๐ฎ๐ฟ๐ฎ๐บ๐ฒ๐๐ฒ๐ฟ๐ and ๐บ๐ผ๐ฑ๐ฒ๐น ๐ฝ๐ฎ๐ฟ๐ฎ๐บ๐ฒ๐๐ฒ๐ฟ๐? What is the difference between theโฆ twitter.com/i/web/status/1โฆ
What are ๐ฝ๐ฎ๐ฟ๐ฎ๐บ๐ฒ๐๐ฒ๐ฟ๐ and ๐บ๐ผ๐ฑ๐ฒ๐น ๐ฝ๐ฎ๐ฟ๐ฎ๐บ๐ฒ๐๐ฒ๐ฟ๐? What is the difference between theโฆ twitter.com/i/web/status/1โฆ
Vladimir Haltakov
@haltakov
This is the best explanation of False Positives and False Negatives... pic.twitter.com/9A5gjL47gU
Vladimir Haltakov
@haltakov
Missing values in real world datasets are inevitable.
How to deal with them? You can either:
Remove them
Fillโฆ twitter.com/i/web/status/1โฆ
How to deal with them? You can either:
Remove them
Fillโฆ twitter.com/i/web/status/1โฆ
Vladimir Haltakov
@haltakov
How to detect objects using CNNs?
Convolutional Neural Networks (CNNs) are very good at classifying images.โฆ twitter.com/i/web/status/1โฆ
Convolutional Neural Networks (CNNs) are very good at classifying images.โฆ twitter.com/i/web/status/1โฆ
...but wait! There's more!
12.
fakhright
@fakhright
astaghfirullah peng.krim guaaaaaaaa..............a *salto sambil solat*
