Flashcards in Intro Deck (33):
What is normal programming vs machine learning?
Normal programming is putting rules to get input to output
Machine learning is giving the input and output and generating the rules
What are convolutional networks best for?
Computer vision and identifying images.
What is an autoencoder?
network architecture used for image compression and denoising
What is transfer learning?
Used to classify things a set has never seen before?
What are recurrent neural networks best for?
Data that forms sequences like text, music, and time series data.
Generative adversarial networks are best for
Recurrent Neural Network
Generative Neural Networks
What is Sci-Kit learn
Machine Learning library for Python
The simplest forms of a neural network
Gradient descent is
A process by which Machine Learning algorithms learn to improve themselves based on the accuracy of their predictions.
The process by which neural networks learn how to improve individual parameters
An extremely popular library for scientific computing in python
One of the most popular python libraries for creating neural networks. It is maintained by Google.
Command to create a new conda environment
conda create -n name_of_env python=3
To enter a conda environment
source activate name_of environment
To see a list of my conda environments
conda info --envs
To see a list of the packages installed in a conda
To add a version to conda use (numpy as an example)
conda install numpy=1.10
To update all conda packages
conda update --all
Which of these commands would you use to install the packages numpy and pandas with conda?
conda install pandas
conda install numpy pandas
Pandas includes numpy
To export conda packages
conda env export > environment.yaml
How did Jupyter Notebooks start?
grew out of the IPython project started by Fernando Perez
What are magic keywords?
special commands you can run in cells that let you control the notebook itself or perform system calls such as changing directories
JN % is
JN %% is for
To test for how fast something completes in JN run
To test for how long your cell takes to run in RN
%%timeit on the top of the cell
To render figures directly in the JN notebook, you should use the inline backend with the command
To render higher quality images in JN
%config InlineBackend.figure_format = 'retina'
To turn on the interactive Python debugger in JN use
To convert a JN to html
jupyter nbconvert --to html notebook.ipynb