What does latent space capture in data? The underlying structure and essential features The irrelevant details The noise and outliers The raw data points

The underlying structure and essential features

intro to ai = exam03

Flashcard

Learn Mode

Match

Library

Create

Flashcards

Library

Match (Coming Soon)

Computer Science - Artificial Intelligence

khalid1090phgs Created by 7 mon ago

Cards in this deck(62)

What is a subset of machine learning that focuses on utilizing artificial neural networks for tasks like classification and regression?

What does the term 'deep' refer to in deep learning?

What is the space containing all possible inputs to a model called?

What is a typically lower-dimensional representation of high-dimensional data?

What does latent space capture in data?

What is the method used by support vector machines to implicitly project data into higher dimensions?

What type of neural network has data flowing from input to output with no loops or cycles?

Why can't we use gradient descent for the step function?

What is a type of transfer learning that involves retraining a pre-trained neural network model on new data?

What is a layer in a neural network that connects every neuron in one layer to every neuron in the next layer?

What are mathematical functions that introduce non-linearity to the network?

What is an activation function that converts a vector of real numbers into a probability distribution?

What is commonly used on the final activation in a neural network to give classification probabilities?

What is an optimization method that iteratively tries to find a set of weights that minimizes the loss?

What measures the difference between a model's predicted output and the actual target value?

What is the slope of a curve at a given point in a specified direction?

What is the gradient we're descending when using gradient descent, and what do we take the partial derivatives with respect to?

What does a loss function need to be for effective optimization?

How is a loss function differentiable?

How is a loss function convex?

What is a method used for hyperparameter tuning by exhaustively trying every combination of hyperparameter values?

What does backpropagation enable in neural networks?

What is a technique in deep learning to efficiently calculate the gradients for a network?

What is the difference between forward differentiation and backward differentiation?

What issues appear when using backpropagation?

What is the vanishing gradient problem using the sigmoid function?

What is the exploding gradient problem?

What type of data requires maintaining some sense of information over time?

What problem do Recurrent Neural Networks solve?

What is a Recurrent Neural Network (RNN)?

What is a key feature of Recurrent Neural Networks?

How do Recurrent Neural Networks process information over time?

What is the equation for recurrent neural networks?

Why use tanh as the activation function for RNN?

What are the pros of RNN?

What are the cons of RNN?

What problem are RNNs prone to?

What are the improvements of RNN?

What do LSTMs introduce to help solve the vanishing gradient problem?

What does the update gate determine in LSTMs?

What does the relevance gate determine in LSTMs?

What does the forget gate determine in LSTMs?

What does the output gate determine in LSTMs?

When are the gates in LSTMs trained?

What are LSTMs prone to?

What is the solution to solving LSTMs' exploding gradient problem?

How do GRUs compare to LSTMs in terms of complexity?

What do GRUs do to the gate structure of LSTMs?

What is one benefit of using GRUs over LSTMs?

What gates are used in LSTMs vs GRUs?

What enables computers to understand and communicate with human language?

What is the first step in Natural Language Processing?

What is the process of splitting a piece of input text into its components?

What are the different levels of tokenization?

What is the goal of tokenization in NLP?

What is the collection of all input texts to the model called?

What do tokens represent in NLP?

What is created in NLP to represent words?

What are word embeddings?

What are embeddings that are the same regardless of context called?

What can be done if we get a context vector from NLP?

What is the mechanism through which a model can focus on important parts of input?

Ask Our AI Tutor

Get Instant Help with Your Questions

Need help understanding a concept or solving a problem? Type your question below, and our AI tutor will provide a personalized answer in real-time!

How it works

Ask any academic question, and our AI tutor will respond instantly with explanations, solutions, or examples.

Get Started

Browse questions and discover topic-based flashcards
Practice with engaging flashcards designed for each subject
Strengthen memory with concise, effective learning tools

Discover By Topic

intro to ai = exam03

Related Decks