DEEP LEARNING
Introduction to Jupyter Notebook,
Anaconda and Phyton DL Tools
Adrian Horzyk AGH University of
Science and Technology
[email protected] Krakow, Poland
Scope
✓ Python – a modern language often used for
AI, CI, KE, and DM computing.
✓ Jupyter Notebook – a modern and intuitive
programming environment with linked
libraries (like Tensorflow, Keras) that allow
to effectively process deep learning
algorithms and present results quickly.
✓ Tensorflow and Keras libraries produced by
leading IT companies, like Google, that
facilitate and simplify implementation and
use of deep learning algorithms and
networks.
Jupyter Notebook
The Jupyter Notebook:
• is an open-source web application that allows you to create and share
documents that contain live code, equations, visualizations, and narrative text;
• includes data cleaning and transformation, numerical simulation, statistical
modeling, data visualization, machine learning, and much more.
We will use it to demonstrate various algorithms, so you are asked to install it.
Jupyter in your browser Install a Jupyter Notebook
Jupyter Notebook & Anaconda
Install Jupyter using Anaconda with built in Python 3.7+
• It includes many other commonly used packages for scientific computing, data
science, machine learning, and computational intelligence libraries.
• It manages libraries, dependencies, and environments with Conda.
• It allows developing and training various machine learning and deep learning
models with scikit-learn, TensorFlow, Keras, Theano etc.
• It supplies us with data analysis including scalability and performance with Dask,
NumPy, pandas, and Numba.
• It quickly visualizes results with Matplotlib, Bokeh, Datashader, and Holoviews.
And run it at the Terminal
(Mac/Linux) or Command
Prompt (Windows):
Anaconda Cloud
Jupyter Notebook & PyCharm
It is recommended to install PyCharm for Anaconda:
Jupyter Notebook
PyCharm is a python IDE for Professional Developers
• It includes scientific mode to interactively analyze your data.
Jupyter Notebook Dashboard
Running a Jupyter Notebook
in your browser:
• When the Jupyter Notebook
opens in your browser, you will see
the Jupyter Notebook Dashboard,
which will show you a list of
the notebooks, files, and
subdirectories in the directory
where the notebook server was
started by the command line
„jupyter notebook”.
• Most of the time, you will wish to
start a notebook server in the highest
level directory containing notebooks.
Often this will be your home
directory.
Starting a new Python notebook
Start a new Python notebook:
• Clicking New → Python 3
• And a new Python project in the Jupyter Notebook will be started:
Useful Packages and Libraries
In the next assignments and examples, we well use the following packages:
• numpy is the fundamental package for scientific computing with Python.
• h5py is a common package to interact with a dataset that is stored on an H5 file.
• matplotlib is a famous library to plot graphs in Python.
• PIL and scipy are used here to test your model with your own picture at the end.
They must be imported:
Let’s start with powerful computations!
✓ Questions?
✓ Remarks?
✓ Suggestions?
✓ Wishes?
Bibliography and Literature
1. Nikola K. Kasabov, Time-Space, Spiking Neural Networks and Brain-Inspired Artificial
Intelligence, In Springer Series on Bio- and Neurosystems, Vol 7., Springer, 2019.
2. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016, ISBN 978-
1-59327-741-3 or PWN 2018.
3. Holk Cruse, Neural Networks as Cybernetic Systems, 2nd and revised edition
4. R. Rojas, Neural Networks, Springer-Verlag, Berlin, 1996.
Adrian Horzyk
5. Convolutional Neural Network (Stanford)
[email protected]6. Visualizing and Understanding Convolutional Networks, Zeiler, Fergus, ECCV 2014 Google: Horzyk
7. IBM: https://www.ibm.com/developerworks/library/ba-data-becomes-knowledge-
1/index.html
8. NVIDIA: https://developer.nvidia.com/discover/convolutional-neural-network
9. JUPYTER: https://jupyter.org/
University of Science
and Technology
in Krakow, Poland
