SlideShare a Scribd company logo

Deep learning

•Download as PPTX, PDF•
•
S
sunilkumar4932

This document provides an overview of deep learning, including definitions, origins, applications, and limitations. It defines deep learning as a machine learning technique that uses multiple layers to learn representations of data. Deep learning algorithms attempt to learn multiple levels of representation using a hierarchy of layers. While deep learning has been used since around 2000, it has grown as a subset of machine learning focused on deep artificial neural networks. Deep learning can learn both unsupervised and supervised and is useful for tasks like speech recognition, natural language processing, image recognition, and self-driving cars. However, it requires large amounts of data and time to train models.

Related slideshows

Convolution Neural Network (CNN)
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
 
Artificial Neural Networks - ANN
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
 
Cnn
CnnCnn
Cnn
 
1 of 15
BASICS OF DEEP LEARNING 1 Made by Sunil kumar pandit
Contents 2  What is Deep leaning?  Origin of Deep learning  Why is DL used?  Al vs ML vs DL  Deep neural network  Application  Limitation
What is Deep Learning ? 3  A machine learning subfield of learning representations of data. Exceptional effective at learning patterns.  Deep learning algorithms attempt to learn (multiple levels of) representation by using a hierarchy of multiple layers
Origin of Deep Learning 4  If machine learning is a subfield of artificial intelligence, then deep learning could be called a subfield of machine learning. The evolution of the subject has gone artificial intelligence > machine learning > deep learning.  The expression “deep learning” was first used when talking about Artificial Neural Networks (ANNs) by Igor Aizenberg and colleagues in or around 2000.
Why is DL used ? 5 o Learned Features are easy to adapt, fast to learn o Deep learning provides a very flexible, universal, learnable framework for representing world, visual and linguistic information. o Can learn both unsupervised and supervised o Utilize large amounts of training data
AI vs ML vs DL 6  Artificial intelligence is the study of how to build machines capable of carrying out tasks that would typically require human intelligence.  Machine learning is the process of teaching a computer to carry out a task, rather than programming it how to carry that task out step by step.  Deep learning is a subset of machine learning. Usually , when people use term deep learning, they are referring to deep artificial neural network .
AI vs ML vs DL 7
Deep Neural Network 8  A deep neural network (DNN) is an artificial neural network (ANN) with multiple layers between the input and output layers. The DNN finds the correct mathematical manipulation to turn the input into the output, whether it be a linear relationship or a non-linear relationship. The network moves through the layers calculating the probability of each output
9
Application 10  Automatic speech recognition
11  Natural language processing
12  Image recognition
13  Self-driving cars
Limitation 14  I think the biggest obstacle to Deep Learning is the need to have HUGE amount of data.  It is very time-consuming .  The main limitation and challenging task in Deep learning is to reduce the complicity of network. In normal deep learning technique there are more than 20 layers.
Thank you 15

More Related Content

Deep learning

  • 1. BASICS OF DEEP LEARNING 1 Made by Sunil kumar pandit
  • 2. Contents 2  What is Deep leaning?  Origin of Deep learning  Why is DL used?  Al vs ML vs DL  Deep neural network  Application  Limitation
  • 3. What is Deep Learning ? 3  A machine learning subfield of learning representations of data. Exceptional effective at learning patterns.  Deep learning algorithms attempt to learn (multiple levels of) representation by using a hierarchy of multiple layers
  • 4. Origin of Deep Learning 4  If machine learning is a subfield of artificial intelligence, then deep learning could be called a subfield of machine learning. The evolution of the subject has gone artificial intelligence > machine learning > deep learning.  The expression “deep learning” was first used when talking about Artificial Neural Networks (ANNs) by Igor Aizenberg and colleagues in or around 2000.
  • 5. Why is DL used ? 5 o Learned Features are easy to adapt, fast to learn o Deep learning provides a very flexible, universal, learnable framework for representing world, visual and linguistic information. o Can learn both unsupervised and supervised o Utilize large amounts of training data
  • 6. AI vs ML vs DL 6  Artificial intelligence is the study of how to build machines capable of carrying out tasks that would typically require human intelligence.  Machine learning is the process of teaching a computer to carry out a task, rather than programming it how to carry that task out step by step.  Deep learning is a subset of machine learning. Usually , when people use term deep learning, they are referring to deep artificial neural network .
  • 7. AI vs ML vs DL 7
  • 8. Deep Neural Network 8  A deep neural network (DNN) is an artificial neural network (ANN) with multiple layers between the input and output layers. The DNN finds the correct mathematical manipulation to turn the input into the output, whether it be a linear relationship or a non-linear relationship. The network moves through the layers calculating the probability of each output
  • 9. 9
  • 14. Limitation 14  I think the biggest obstacle to Deep Learning is the need to have HUGE amount of data.  It is very time-consuming .  The main limitation and challenging task in Deep learning is to reduce the complicity of network. In normal deep learning technique there are more than 20 layers.