Scribd
Upload
77 views10 pages

DL Mod1.PDF Flashcards

Deep learning is a machine learning subfield focused on training artificial neural networks inspired by the human brain. Key components include neural networks, activation functions, loss functions, and backpropagation, with transfer learning enhancing efficiency. Its importance lies in its ability to learn complex data representations, improve performance on large datasets, and simplify system design.

Uploaded by

digitalpioneer30
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
77 views10 pages

DL Mod1.PDF Flashcards

Deep learning is a machine learning subfield focused on training artificial neural networks inspired by the human brain. Key components include neural networks, activation functions, loss functions, and backpropagation, with transfer learning enhancing efficiency. Its importance lies in its ability to learn complex data representations, improve performance on large datasets, and simplify system design.

Uploaded by

digitalpioneer30
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Question 1:

What is deep learning and what are its main inspirations?

Answer 1:
Deep learning is a subfield of machine learning that focuses on training
artificial neural networks to perform tasks without explicit
programming, inspired by the structure and function of the human
brain.
Question 2:

What are the core components of deep learning?

Answer 2:
The core components of deep learning include neural networks,
activation functions, training data and labels, loss function,
backpropagation, deep learning architectures, transfer learning, and
frameworks and libraries.
Question 3:

What is the purpose of activation functions in neural networks?

Answer 3:

Activation functions introduce non-linearity into the model, enabling it


to learn complex relationships within the data.
Question 4:

What is the role of the loss function in training deep learning models?

Answer 4:
The loss function measures the difference between the predicted
output and the actual target, guiding the model to minimize this loss
during training.
Question 5:

What is backpropagation in the context of deep learning?

Answer 5:
Backpropagation is an optimization algorithm used to update the
model's parameters during training, by calculating the gradient of the
loss function and adjusting the parameters to minimize the loss.
Question 6:

What is transfer learning and why is it beneficial?

Answer 6:
Transfer learning involves using pre-trained models from one task as a
starting point for another task, leveraging knowledge from large
datasets to save computation time and resources.
Question 7:

What distinguishes deep neural networks from shallow networks?

Answer 7:
Deep neural networks have multiple hidden layers, which allows them
to capture complex hierarchical patterns, while shallow networks
typically have only one or two hidden layers.
Question 8:

What are some common types of shallow networks?

Answer 8:
Common types of shallow networks include Single-Layer Perceptron
(SLP), Multilayer Perceptron (MLP) with one hidden layer, Radial Basis
Function (RBF) Networks, Extreme Learning Machines (ELM), Cascade
Correlation Networks, and Generalized Regression Neural Network
(GRNN).
Question 9:

How does the input to the hidden layer in shallow networks get
computed?

Answer 9:
The input to the hidden layer is calculated as the weighted sum of the
input features, followed by the addition of biases and often passed
through an activation function.
Question 10:

Why is deep learning considered important in modern technology?

Answer 10:
Deep learning is important because it automatically learns hierarchical
representations from data, improves performance on large datasets, is
versatile across various tasks, and simplifies system design through end-
to-end learning.

You might also like