The main reason people think they can’t begin with machine learning deep learning is the lack of hardware. not having a GPU results in slow training of models.
Google has released its new product Colaboratory which is a free Jupyter notebook environment that requires no setup and runs entirely in the cloud.
what is Colaboratory?
Colaboratory is a research tool for machine learning education and research. It’s a Jupyter notebook environment that requires no setup to use.
If you have already used jupyter notebook you might find it simple to use. Colaboratory is based on jupyter. Colaboratory allows you to use and share Jupyter notebooks with others without having to download, install, or run anything on your own computer other than a browser.
Colaboratory supports Python 2.7 and Python 3.6. Also supports GPU enabled jupyter notebooks.
Overview of Colaboratory
A notebook is a list of cells. Cells contain either explanatory text or executable code and its output. Click a cell to select it.
Working with python
We can easily work on python 2.X or 3.X using Colaboratory.
Importing libraries and installing dependencies
Colab comes with pre-installed libraries like Keras, TensorFlow is available by default but you can switch which version you’re using.
Importing a library that is not in Colaboratory
To import a library that’s not in Colaboratory by default, you can use
!pip install or
we are using patient medical record data for Pima Indians and whether they had an onset of diabetes within five years.
Patient Diabetes prediction using Keras on Colaboratory
I was successfully able to train the model on Colab. It is simple and better way of learning machine learning and deep learning on cloud
Originally published at medium.com on September 15, 2018.
Source: Deep Learning on Medium