8 - Machine Learning Flashcards
Why Machine Learning?
Allows for more complex thinking and decision making
Definition of Machine Learning
Describes computer algorihms that can improve automatically through experience and by the use of data
What is Supervised Learning?
The machine uses labeled training data
Told the correct input to course correct its current position
What is Unsupervised Learning?
Data isn’t labeled
The machine figures out how to deal with the problem on its own
Discovers unknown patterns in data
What is Reinforcement Learning?
Gives the machine the most freedom
Uses trial and error to figre out the best solution
What is a Neural Network?
The ability for a network to analyze large amounts of data and make the best decision based off the data
You can provide parameters for the macine to look for
Definition of a Feature
An input variable used in making predictions
Definition of Weight
A coefficient for a feature in a linear model, or an edge in a deep network
Definition of Bias
An intercept or offset to the model
Tells the program if it meets criteria and affects the choice
Definition of Neuron
A node in a neural network
Takes in multiple inputs to create one output value
Definition of an Activation Function
A function that takes the output of the previous problem and forwards that output to the next criteria
If…then…
ReLU or sigmoid
Definition of Hidden Layer
A synthetic layer in a neural network between the input layer (the features) and the output layer (the prediction).
Contains an activation function (bounds the output of a neuron) for training.
Definition of Epoch
A full training pass over the entire dataset such that each example has been seen once
“Iterations of data”
Breakdown of “Prepared Data”
- Training Data
- Test Data
What is a Confusion Matrix?
A tool used to confirm how accurate the findings are
Diagnol findings are the most accurate
