Let_s_Dive_to_Deep_Learning.pptx
0 likes•13 views
This document provides an overview of deep learning. It defines deep learning as a subset of machine learning that uses neural network architectures, especially deep neural networks containing many hidden layers. Deep learning models are trained on large labeled datasets to automatically extract features without manual feature engineering. Convolutional neural networks are commonly used for tasks like image classification by extracting hierarchical features from images. The document outlines the basic architecture of CNNs including convolutional layers that extract features and pooling layers that reduce size, as well as fully connected layers. It also briefly describes the learning process of forward and backward propagation.
Let_s_Dive_to_Deep_Learning.pptx
- 1. Let’s Dive to Deep Learning “Computers are able to see hear and learn welcome to the future.” By. Mohamed Essam
- 2. What is Deep Learning? In the last few years of the IT industry, there has been a huge demand for once particular skill set known as Deep Learning(Neural Network is the back bone of deep learning).
- 3. What is Deep Learning? Deep learning is a subset of methods for machine learning which is a field dedicated to the study and development of machines that can learn (sometimes with the goal of eventually attaining general artificial intelligence).
- 4. What is Deep Learning?
- 5. Geoffrey Hinton is a pioneer in the field of artificial neural networks and co-published the first paper on the backpropagation algorithm for training multilayer perceptron networks. He may have started the introduction of the phrasing “deep” to describe the development of large artificial neural networks. Why Call it “Deep Learning“? Why Not Just “Artificial Neural Networks“?
- 6. Examples of Deep Learning at Work Automated Driving: Automotive researchers are using deep learning to automatically detect objects such as stop signs and traffic lights.
- 7. Examples of Deep Learning at Work Medical Research: Cancer researchers are using deep learning to automatically detect cancer cells. Teams at UCLA built an advanced microscope that yields a high-dimensional data set used to train a deep learning application to accurately identify cancer cells.
- 8. Examples of Deep Learning at Work Electronics: Deep learning is being used in automated hearing and speech translation. For example, home assistance devices that respond to your voice and know your preferences are powered by deep learning applications.
- 9. How Deep Learning Works Most deep learning methods use neural network architectures, which is why deep learning models are often referred to as deep neural networks.
- 10. How Deep Learning Works The term “deep” usually refers to the number of hidden layers in the neural network. Traditional neural networks only contain 2-3 hidden layers, while deep networks can have as many as 150. Deep learning models are trained by using large sets of labeled data and neural network architectures that learn features directly from the data without the need for manual feature extraction.
- 11. How Deep Learning Works One of the most popular types of deep neural networks is known as convolutional neural networks (CNN or ConvNet). CNN is a type of neural network model which allows us to extract higher representations for the image content. Unlike the classical image recognition where you define the image features yourself, CNN takes the image's raw pixel data, trains the model, then extracts the features automatically for better classification.
- 12. Difference Between ML and Deep Learning Deep learning is a specialized form of machine learning. A machine learning workflow starts with relevant features being manually extracted from images. The features are then used to create a model that categorizes the objects in the image. With a deep learning workflow, relevant features are automatically extracted from images. In addition, deep learning performs “end-to-end learning” – where a network is given raw data and a task to perform, such as classification, and it learns how to do this automatically.
- 15. How Deep Learning Works CNNs eliminate the need for manual feature extraction, so you do not need to identify features used to classify images. The CNN works by extracting features directly from images. The relevant features are not pretrained; they are learned while the network trains on a collection of images. This automated feature extraction makes deep learning models highly accurate for computer vision tasks such as object classification.
- 16. Basic Architecture of Convolutional neural networks There are two main parts to a CNN architecture A convolution tool that separates and identifies the various features of the image for analysis in a process called as Feature Extraction. A fully connected layer that utilizes the output from the convolution process and predicts the class of the image based on the features extracted in previous stages.
- 18. Basic Architecture of Convolutional neural networks 1. Convolutional Layer This layer is the first layer that is used to extract the various features from the input images. In this layer, the mathematical operation of convolution is performed between the input image and a filter of a particular size MxM.
- 22. Basic Architecture of Convolutional neural networks 1. Convolutional Layer By sliding the filter over the input image, The output is termed as the Feature map which gives us information about the image such as the corners and edges. 120 202 12 0 21 34 32 98 73 37 27 38 93 57 74 31 28 23 45 55
- 23. Basic Architecture of Convolutional neural networks 1. Convolutional Layer 120 202 12 0 21 34 32 98 73 37 27 38 93 57 74 31 28 23 45 55
- 24. Basic Architecture of Convolutional neural networks 1. Convolutional Layer 120 202 12 0 21 34 32 98 73 37 27 38 93 57 74 31 28 23 45 55
- 25. Basic Architecture of Convolutional neural networks 1. Convolutional Layer 120 202 12 0 21 34 32 98 73 37 27 38 93 57 74 31 28 23 45 55
- 26. Basic Architecture of Convolutional neural networks 2. Pooling Layer In most cases, a Convolutional Layer is followed by a Pooling Layer. The primary aim of this layer is to decrease the size of the convolved feature map to reduce the computational costs. This is performed by decreasing the connections between layers and independently operates on each feature map. Depending upon method used, there are several types of Pooling operations.
- 27. Basic Architecture of Convolutional neural networks In Max Pooling, the largest element is taken from feature map. Average Pooling calculates the average of the elements in a predefined sized Image section. The total sum of the elements in the predefined section is computed in Sum Pooling. The Pooling Layer usually serves as a bridge between the Convolutional Layer and the FC Layer.
- 28. Basic Architecture of Convolutional neural networks 3. Fully Connected Layer The Fully Connected (FC) layer consists of the weights and biases along with the neurons and is used to connect the neurons between two different layers. These layers are usually placed before the output layer and form the last few layers of a CNN Architecture.
- 30. Learning Process Forward Propagation Backward Propagation
- 31. Learning Process
- 32. Learning Process
- 33. Learning Process
- 34. Learning Process
- 36. CREDITS: This presentation template was created by Slidesgo, including icons by Flaticon, and infographics & images by Freepik THANKS! Contacts [email protected] Please keep this slide for attribution