|
Created by August Edström
almost 6 years ago
|
|
What is machine learning?
What is the difference between supervised and unsupervised learning
What is special about reinforcement learning?
How is the output of a node determined?
How is the error handled in a neural network?
How can input be encoded?
Why is input encoding needed?
What does the distributional hypothesis say?
A standard neural network has a single set of weights, a recurrent neural network (RNN) has two sets of weights, and a Long Short Term Memory (LSTM) network has three sets of weights. What is the purpose of the extra sets of weights for the RNN and LSTM models?
What is the purpose of a word embedding in text classification?
Given the words 'pizza', 'pasta' and 'recursion', construct 5-dimensional word embeddings with two significant digits for each word such that the semantic similarity between the words is preserved.