What is Long-Short Term Memory (LSTM)?
LSTM is an enhancement used to improve the performance of a Recurrent Neural Network
Deep Learning
Briefly describe the architecture of a Recurrent Neural Network (RNN) and how it addresses the shortcomings of traditional Neural Networks.
The Recurrent Neural Network (RNN) is designed to work with data that naturally exists as part of a sequence
What is the difference between a Batch and an Epoch?
In Neural Networks, a batch is a subset of the training data that the network sees before the parameters are updated.
What is Dropout?
Dropout refers to randomly turning off hidden units so that a smaller network is trained on a given pass
What are some options to address overfitting in Neural Networks?
One of the main drawbacks of deep learning is that it is more prone to overfitting
What are some ways to address the vanishing/exploding gradient issue?
The following are some options that have been shown to reduce the risk of experiencing a vanishing or exploding gradient
What is the vanishing/exploding gradient problem?
The vanishing or exploding gradient is an issue often encountered in the training of deep Neural Networks.
What are some options for making Backpropagation more efficient?
In a deep network with many hidden layers, it can be very computationally intensive to compute derivatives of all of the parameters of the network.
What is Backpropagation?
In Backwards Propagation, the parameters of a Neural Network (all of the weight and bias terms) are updated using a gradient descent optimization
How are Regression and Classification performed using multilayer perceptrons (MLP)?
Multilayer perceptrons models are suitable for both regression and classification tasks