Deep Learning Flashcards
How is Deep Learning defined?
Deep learning is a subfield of machine learning that uses artificial neural networks with multiple hidden layers to extract complex patterns and representations from data. Deep learning is a modularized approach to machine learning.
What constitutes a “deep” neural network?
A deep neural network is a neural network with many hidden layers. For example, AlexNet, VGG, and GoogleNet are examples of deep neural networks.
What is a fully connected feedforward network?
In a fully connected feedforward network, each neuron in one layer is connected to every neuron in the subsequent layer.
How does deep learning address the need for feature engineering?
Deep learning models perform automatic feature engineering, learning relevant features from the data, rather than relying on manually designed ones.
What is modularization in the context of deep learning?
The sources do not explicitly define this concept. However, it can be inferred that deep learning uses modularization to break down complex tasks into simpler classifiers. For example, an image classifier can be broken down into classifiers for attributes such as ‘long or short hair’ and ‘cat or dog’.
What is an advantage of using multiple layers in deep networks?
Using multiple layers allows the network to represent complex functions in a simpler way, requiring fewer parameters than with a single layer, and fewer logic gates
What are hidden layers in deep networks?
Hidden layers are layers of neurons that exist between the input and output layers. They are responsible for learning complex patterns in the data.
