Deep Learning Kathi

G PULLAIAH COLLEGE OF ENGINEERING AND TECHNOLOGY
(AUTONOMOUS)
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
DEEP LEARNING
SEMINAR SUPERVISOR
P. RAMA RAO M.Tech
Assistant Professor
Presented by
K. Sucharitha
16AT1A0590
CONTENTS
What is Deep Learning
Languages which uses DL
Why it is important
Deep Learning Process
Types of Deep Learning Networks
Applications
Future Predictions
conclusion
WHAT IS DEEP LEARNING
Deep learning is a computer software that mimics the network of
neurons in a brain. It is a subset of machine learning and is called
deep learning because it makes use of deep neural networks.
 Deep Learning is a particular kind of machine learning that
achieves great power and flexibility by learning to represent the
world as a nested hierarchy of concepts, with each concept defined
in relation to simpler concepts, and more abstract representations
computed in terms of less abstract ones.
Languages which uses DL
Python
Matlab
Java
Julia
Java Script
R Programming
WHY IT IS IMPORTANT
DEEP LEARNING PROCESS
Understand the problem
Identify Data
Select Deep Learning Algorithm
Training the Model
Test the Model
TYPES OF DL NETWORKS
Feed-Forward Neural Networks
Recurrent Neural Networks
Convolution Neural Networks
Reinforcement Learning
Feed-Forward Neural Networks
The simplest type of artificial neural network. With this type of
architecture, information flows in only one direction, forward.
 It means, the information's flows starts at the input layer, goes
to the "hidden" layers, and end at the output layer. The network
does not have a loop. Information stops at the output layers.
Recurrent Neural Networks
RNN is a multi-layered neural network that can store
information in context nodes, allowing it to learn data sequences
and output a number or another sequence.
In simple words, it is an artificial neural networks whose
connections between neurons include loops. RNNs are well
suited for processing sequences of inputs.
These networks are used to help security traders to generate
analytical reports.
It provides caption for the images.
Convolution Neural Networks
CNN is a multi-layered neural network with a unique
architecture designed to extract increasingly complex features of
the data at each layer to determine the output.
CNN's are well suited for perceptual tasks.
CNN is mostly used when there is an unstructured data set
(e.g., images) and the practitioners need to extract information
from it.
Reinforcement Learning
Reinforcement learning is a subfield of machine learning in
which systems are trained by receiving virtual "rewards" or
"punishments," essentially learning by trial and error.
 Google's DeepMind has used reinforcement learning to beat a
human champion in the Go games.
Reinforcement learning is also used in video games to improve
the gaming experience by providing smarter bot.
APPLICATIONS
Self-Driving Cars
Voice Search and Voice-Activated Assistants
Automatic Machine Translation
Image Recognition
Automatic Image Caption Generation
Automatic Colorization
Predicting Earthquakes
Self-Driving Cars Voice Search and
Voice activated Assistants
Automatic Machine Image
Translation Recognition
Automatic Image Caption Automatic
Generation Colorization
FUTURE PREDICTIONS
Within the next five to 10 years, deep learning development tools, libraries,
and languages will become standard components of every software
development toolkit.
User-friendly deep learning development capabilities will be embedded
in generative design tools used by artists, designers, architects, and creative
people of all stripes who would never go near a neural network.
 Driving this will be a popular mania for deep learning-powered tools for
image search, auto tagging, photorealistic rendering, style transformation ,
resolution enhancement, and music composition.
As the deep learning market advances toward mass adoption, it will follow in
the footsteps of data visualization, business intelligence, and predictive
analytics markets.
CONCLUSION
Deep Learning (DL) has a big scope in future and the biggest reason for it is
that DL doesn’t require any kind of feature engineering. Deep Learning
extracts the features from the data itself instead of us giving it the features
after extracting it from the data. Today, Deep Learning will take different
paths for development. Deep Learning with Quantum Computing
Technology has tremendous potential to change and build a deep
compassionate human society. It will change the dynamics of the society
starting from child care, relationship management to military affairs,
commerce, and maintaining strategic balance of power.
Thank
You

Deep Learning Kathi

Uploaded by

Copyright:

Available Formats

Deep Learning Kathi

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Deep Learning Kathi

Uploaded by

Copyright:

Available Formats

G PULLAIAH COLLEGE OF ENGINEERING AND TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

You might also like