Week 1 Comprehensive

Week 1 Comprehensive >> Introduction to Machine Learning

Labeled training data

A model

Learning from data

Human to teach the machine

Smooth curves

Linear

Arbitrarily complex functions

Jagged edges

This allows the model to look for subtypes of the classification.

This requires less compute power.

This is simpler to implement.

More complexity is always better.

Parameters at the top of the model are transferable across all people and documents, while the parameters at the bottom are different between individuals.

Parameters at the bottom of the model are transferable across all people and documents, while the parameters at the top are different between individuals.

All parameters of the model are transferable across all people and documents.

All parameters of the model are different between individuals.

Logistic regression

Multilayer perceptron

A new computational platform: the GPU

A new operation: convolution

A new application: image search

A new name: Deep Learning

Layer 1 feature map

Layer 2 feature map

Layer 3 feature map

Stacking a collection of feature maps.

Surveying a feature map for high-level motif.

Selecting an atomic element from an image.

Shifting a filter to every location in an image.

Sufficient labeled radiological images can be used to learn all of the model parameters, so they can be used for ophthalmological or dermatological images.

Weights of convolutional layers learned from ImageNet transfer to medical images, so we only need learn new parameters at the top of the network.

Once the convolutional layers are learned from labeled medical images, the top layers can be inferred from the parameters found with data from ImageNet.

Just as assigning categories to images in ImageNet required millions of images, so too does analyzing medical images require millions of labeled medical images.

The parameters of a deep architecture are less expensive to compute.

A model can learn each top-level motif in isolation.

There is a higher probability that each motif is used in the classifier.

The model shares knowledge between motifs through their shared substructures.

Week 1 Comprehensive >> Introduction to Machine Learning

Related Questions & Answers:

Leave a Comment Cancel reply