Week 3 Comprehensive

Week 3 Comprehensive >> Introduction to Machine Learning

Likelihood Ratio

Positive Predictive Value

Specificity

Sensitivity

Negative Predictive Value

Specificity

Sensitivity

False Negative

“Intertwining” of two signals, where one wraps around the other to form a feature.

“Distortion” of one signal, according to the feature shape

“Sliding” of two signals, where a matched feature gives a high value of convolution.

“Inverting” of a shape, where the inversion matches a feature.

The vectorization of a pooling layer.

A layer with a single neuron for each output class.

A layer with connections to all feature maps.

A layer with ten classifications.

Nonlinear activation functions increase the functional capacity of the neural network by allowing the representation of nonlinear relationships between features in input.

Nonlinear activation functions are preferable because they are used in generalized linear models in statistics.

Nonlinear activation functions are preferable because they have been used historically.

Nonlinear activation functions are NOT preferable to linear ones, as they lose information in systems with high variance.

Gradient descent

Fractal geometry

Simplex algorithm

Stochastic gradient descent

Eliminating bias.

Decreasing variance in the model.

Better leveraging all training data.

Decreasing the computational complexity.

Low-level features are specialized for a particular task, while top-level features are universal to all images.

All images are composed of pixels with three color channels.

Top-level features are specialized for a particular task, while low-level features are universal to all images.

All layers of filters can be learned by studying the mammalian receptive fields.

Week 3 Comprehensive >> Introduction to Machine Learning

Related Questions & Answers:

Leave a Comment Cancel reply