Preprocessing - Keras
Here I go over Preprocessing, which is super important when you're working with data and want to do some transformations to it beforehand in order to use it to do machine learning.
I first start of with a brief explanation of simple preprocessing such as making an array of categories categorical, etc. The other type of super basic preprocessing that I go over is the normalization of data (which is something you always want to do).
We then go over sequence preprocessing and where I explain multiple preprocessing concepts and tools such as: “padding” of a sequence of actions; using skipgrams (incredibly useful if you’re doing any "one-hot vector" type stuff); natural language text preprocessing (including an overview of using the classic tokenizer).
Then, we move onto image preprocessing. Here I show you some cool ways to augment your image/data with random shifts and permutations like: image rotation, shifting width and length, sheering images, zooming, horizontal/vertical shift, rescaling, etc) after which I show you all of these image preprocessing techniques in action!
Links:
1) Link to my SciKit Learn Preprocessing video: • Preprocessing in Scikit Learn
2) Link to my SciKit Learn Datasets video: • Datasets in Scikit Learn
3) Link to my Scikit Learn tutorial - A Bit of DataScience and Scikit Learn: • Intro to Scikit Learn
4) The Hitchhiker's Guide to Python - one of the best handbooks to the installation, configuration, and usage of Python that I have come across: http://docs.python-guide.org/en/latest/
5) Link to Keras: https://keras.io
6) Link to TensorFlow: https://www.tensorflow.org
7) GitHub link to a-bit-of-deep-learning-and-keras notebooks: https://github.com/knathanieltucker/a...
8) Link to the History of Deep Learning video will be up soon!
Watch video Preprocessing - Keras online without registration, duration hours minute second in high quality. This video was added by user Data Talks 07 November 2017, don't forget to share it with your friends and acquaintances, it has been viewed on our site 10,694 once and liked it 107 people.