Linear/Logistic Regression
Inputs into a model (i.e. for a house price model, the number of rooms and square footage)
What are features?
This function takes in our estimated output values and true output values, and returns a number representing a difference between the two.
What is a loss function?
The neural network most commonly used for computer vision
What is a convolutional neural network?
Co-founder of Coursera who teaches their "Introduction to Machine Learning" course
Andrew Ng
This model is commonly used for binary classification tasks.
What is logistic regression?
This approach to learning a function makes an initial guess, and adjusts the function based on how “wrong” it was
What is Gradient Descent?
This term encompasses the following steps: using hypothesis function and weights to make predictions, compute cost
What is forward propagation?
The famous person who said this: "With artificial intelligence we are summoning the demon"
Who is Elon Musk?
This function outputs a vector which has elements that sum up to 1
What is softmax function?
Hyperparameter that controls how large of a "step" gradient descent takes
What is learning rate?
This term encompasses these steps: using cost to compute gradients, updating weights
What is backpropagation?
The paper that is considered one of the most influential in deep learning; it is what popularized convolutional neural networks
AlexNet