Advanced Machine Learning Flashcards

You may prefer our related Brainscape-certified flashcards:
1
Q

What is Deep Learning?

A

Deep learning is a subset of machine learning that has become increasingly popular in recent years due to its performance along with improved computer speed.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the process of neural networks?

A
  1. Take our inputs and multiply each input by a weight.
  2. Add the results from step 1 together.
  3. Add a value (called bias) to the result from step 2
  4. Pass result from step 3 through an activation function.
  5. The result from step 4 is then passed to the next layer, where the processed is repeated.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is Node?

A

One unit that process incoming information and produces a single output number

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is layer?

A

A collection of nodes working in parallel

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is Input layer?

A

The first set of nodes that work on the features of the input sample

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is Output layer?

A

The last set of nodes that output a prediction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is Forward Propagation?

A

The processing and passing of information forward through all layers to produce an output prediction

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is cost function?

A

The difference between the predictions of all samples and their true labels

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is Backward Propagation?

A

The process of updating the weights of each node to reduce the cost function

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What is Epoch?

A

The process of completing one forward Propagation step on each sample in the training set and updating the weights of each node with backward Propagation is called an epoch

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is activation functions?

A

They can create non-linear functions to predict class or values

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is sigmoid?

A

The sigmoid function maps all output values of the node to a value between 0 and 1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is Tanh (or hyperbolic tangent)?

A

Tanh maps the output of a node to a value between -1 and 1, as shown above on the y axis of the second plot

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Wha is ReLu (Rectified Linear Unit)?

A

It maps all negative outputs from a node to 0 and returns all positive outputs as is (linear function)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What is Output layer Activation functions?

A

The exception is the output layer. Specific activation functions are required for a model to produce specific kinds of outputs

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What is Linear (regression models)?

A

If the model should have a continuous output that can produce positive or negative. A Linear activation function simply returns the value that was passed to it. g(z) =z.

17
Q

What is sigmoid (binary classification)?

A

If the model should only output 0 or a 1, such as in binary classification problems

18
Q

What is softtmax (multiclass classification models)?

A

If the model should return the most likely candidate from a finite list of options, such as a multiclass classification problem

19
Q

What is ythat?

A

The prediction of a model for all samples in X.

20
Q

What is cost?

A

The combination of all of a model’s errors on all samples

21
Q

What is cost function or loss function?

A

The difference between the predictions of all samples and their true labels

22
Q

What is Gradient Descent?

A

Changing weights to reduce the cost function

23
Q

What is Keras?

A

Keras is an API that acts as an interface for tensorflow, a popular choice for building networks, especially as you are first learning

24
Q

What is Bias?

A

Is is related to underfitting

25
Q

What is Variance?

A

Is it related to overfitting

26
Q

What is CNN?

A

Convolutional Nerual Networks (CNNs) revolutionized computer vision because of how well they do at working with image data.