Intro Flashcards Preview

Deep Learning > Intro > Flashcards

Flashcards in Intro Deck (33):
1

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

2

What are convolutional networks best for?

Computer vision and identifying images.

3

What is an autoencoder?

network architecture used for image compression and denoising

4

What is transfer learning?

Used to classify things a set has never seen before?

5

What are recurrent neural networks best for?

Data that forms sequences like text, music, and time series data.

6

Generative adversarial networks are best for

Image generation

7

RNN SF

Recurrent Neural Network

8

GAN SF

Generative Neural Networks

9

What is Sci-Kit learn

Machine Learning library for Python

10

Percetrons are

The simplest forms of a neural network

11

Gradient descent is

A process by which Machine Learning algorithms learn to improve themselves based on the accuracy of their predictions.

12

Backpropagation is

The process by which neural networks learn how to improve individual parameters

13

Numpy is

An extremely popular library for scientific computing in python

14

Tensorflow is

One of the most popular python libraries for creating neural networks. It is maintained by Google.

15

Command to create a new conda environment

conda create -n name_of_env python=3

16

To enter a conda environment

source activate name_of environment

17

To see a list of my conda environments

conda info --envs

18

To see a list of the packages installed in a conda

conda list

19

To add a version to conda use (numpy as an example)

conda install numpy=1.10

20

To update all conda packages

conda update --all

21

Which of these commands would you use to install the packages numpy and pandas with conda?

conda install pandas
or
conda install numpy pandas
Pandas includes numpy

22

To export conda packages

conda env export > environment.yaml

23

How did Jupyter Notebooks start?

grew out of the IPython project started by Fernando Perez

24

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

25

JN % is

Line magics

26

JN %% is for

cell magics

27

To test for how fast something completes in JN run

%timeit function_name()

28

To test for how long your cell takes to run in RN

%%timeit on the top of the cell

29

To render figures directly in the JN notebook, you should use the inline backend with the command

%matplotlib inline

30

To render higher quality images in JN

%config InlineBackend.figure_format = 'retina'

31

To turn on the interactive Python debugger in JN use

%pdb

32

To convert a JN to html

jupyter nbconvert --to html notebook.ipynb

33

x

x