Scribd
Upload
4 views

module 1 part 3

The document presents an overview of major architectures of deep networks, focusing on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). CNNs are highlighted for their effectiveness in object recognition and feature extraction in images, while RNNs are noted for their capability to process information over time, resembling human brain functions. The document also discusses various applications of both CNNs and RNNs in fields such as computer vision, speech recognition, and natural language processing.

Uploaded by

chintu50802
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views

module 1 part 3

The document presents an overview of major architectures of deep networks, focusing on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). CNNs are highlighted for their effectiveness in object recognition and feature extraction in images, while RNNs are noted for their capability to process information over time, resembling human brain functions. The document also discusses various applications of both CNNs and RNNs in fields such as computer vision, speech recognition, and natural language processing.

Uploaded by

chintu50802
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 19

Deep Learning-2

Presented by
Dr. Jayavrinda Vrindavanam
Professor and Chairperson , Department of CSE(AI and ML)
Dayananda Sagar University
Bengaluru

10/19/2024 DEPARTMENT OF CSE(AI&ML) DSU 1


Major Architectures of Deep Networks:

1. Convolutional Neural Networks (CNNs)


2. Unsupervised Pretrained Networks (UPNs)
3. Recurrent Neural Networks
4. Recursive Neural Networks
• we’ve seen some of the components of deep
networks, let’s take a look at the four major
architectures of deep networks.
• And how we use the smaller networks to build them.
Review of Convolutional Neural Networks(CNNs)

• The goal of a CNN is to learn higher-order features in the data via


convolutions.
• They are well suited to object recognition with images and
consistently top image classification competitions.
• They can identify faces, individuals, street signs, platypuses, and
many other aspects of visual data.
• CNNs overlap with text analysis via optical character recognition,but
they are also useful when analyzing words as discrete
textual units.
• They’re also good at analyzing sound.
Review of Convolutional Neural Networks(CNNs)…

▪ The convolution operation is known as the feature detector of


a CNN.
▪ The input to a convolution can be raw data or a feature map output
from another convolution.

▪ It is often interpreted as a filter in which the kernel filters input data


for certain kinds of information.
▪ Kernels are basically used to extract certain features from the input
image.
Applications of CNN
• Computer vision
• Face recognition
• Scene labelling
• Image classification
• Activity recognition
• Speech recognition
• Text classification for natural language processing
Recurrent Neural Networks
• Recurrent Neural Networks are in the family of feed-
forward neural networks.
• They are different from other feed-forward networks in their
ability to send information over time-steps.
• Recurrent Neural Networks are similar to the human brain.
• which is a large feedback network of connected neurons that
some how can learn to translate a life long sensory input stream
into a sequence of useful motor outputs.
Recurrent Neural Networks….
• The brain is a remarkable role model as it can solve many problems
current machines cannot yet solve.
• These networks have been difficult to train, but more recently,
advances in research have made them more approachable for
the practitioner.
• A Recurrent Neural Network (RNN) is a class of artificial
neural networks where connections between nodes form
a directed graph along a temporal sequence.
Recurrent Neural Networks….
What is RNN….
What is RNN….
What is RNN….
What is RNN….
RNN’s For Sequence Modeling
Applications of RNN….
19

You might also like