Data Mining Machine Learning AI Artificial Intelligence
Yogesh Narayan Singh
Have trainings for 11hours tomorrow.. just got 2 hours of sleep to catch up
Good night guys
Yogesh Narayan Singh
Thnx guys gite:)
I learned about cnn recently and it looks like it can replace many previous systems ... I was building a content based image retrieval system for a school project with some known features in image processing field but when I saw the cnn I feel like it's a replacement for this because it learns the important parts of the image on it's own .. am I right ?
Not exactly @rawan_la_twitter
It can be
but a retrieval system can be way simpler and easier to set up than a CNN
If you just have a content mapping system that say takes a text input...
you could just map it to an image
the data set would be simple/small in comparrison
CNNs are useful when you have a giant Dataset and you need to automate the classification.
dog = picture A of dog
breaks down if someone does Dog walking in th epart next to a black cat
CNN in theory could map any # of mappings automatically to any number of images and would grow and change along with the content and inputs that people use.
For the vast majority of systems you still really just need a mapping system
CMS systems aren't going anywhere
They are good for when there is only 1 answer to a question
thank you @keithaumiller :smile:
can anyone tell me to do some practicals related to data mining and ml quickley, which tutorial you preffer ? I just need to play on some Data Science related stuffs.
This will be my first hands on experince, I'd like to do this untill I familiar with the project what I'm gonna do in campus
@AMFIRNAS This course should be good for getting hands on experience with deep learning: http://www.fast.ai/
Hi All! Can someone please help me with an issue? I'm training a recurrent neural network (with GRU) for a classification problem using rmsprop as an optimizer.
Training loss goes down for the first ~1 million examples, but then starts going up again
Why could it be?
The only reason that I might think of something like that is missclassification
How sure are you that your dataset is right?
And aslso the model might be too small
(I am a student so please take it as a grain of salt)
The dataset is probably noisy. If I reduce dataset size to few hundred thousand examples I get training accuracy above 90%. But even if the dataset is noisy, can it lead to training error increasing over time? I've thought if model capacity is large enough training error should decrease to near 0 (memorize the training set), if capacity is small it should stay flat at some point.
"Understanding Deep Learning Requires Rethinking Generalization" paper shows how neural networks can memorize even random labels
Assuimg you reduce in a random manner, I can only assume that the noisy is made by a model to throw off other models (GAMs by Ian Goodfellow)
Just dropping in a hello in case I sleep and miss the chat again.
Sorry I couldn't make it Friday night guys, I was at the Machine Learning in Finance conference
Feel free to read through my notes and if you have any questions, let me know.
The Goldman Sachs Senior Data scientists I talked to was a really cool guy
Great story about how he went from sleeping in his car, to winning data hackathons in San Fran, to working at GS
Hi, I want to classify a multi labeled data using deep learning techniques like CNN without building multiple classifier for each label.. when I read about it they say that I should use multiple sigmoid units on the last layer with binary cross entropy loss function.. actually I didn't understand why this would work and is there a better way to do this?
I'm availabe for at least the next hour to help out with whatever.
And if any of you know an easy way to parallelize my R scripts I'd love to hear it. ;)
@rawan_la_twitter I haven't done a multi labeled data classification with CNN, but I have done it with neural nets in general.
first step is to change your label data into a binary set
once you get the data out of a one field with multiple values and into multiple fields with binary values it's much easier