2. OUTLINE
• Introduction
• Overview
• What is Deep Learning?
• Evolution
• Brief History
• Basics
• ML vs DL
• Architecture
• ANNs
• DNNs
• Applications
• Classes
• Big players
• Conclusion
Deep Learning
2/12
3. Deep Learning - Overview
WHAT IS DEEP LEARNING?
Part of the machine learning field of learning representations of data.
Exceptional effective at learning patterns.
Utilizes learning algorithms that derive meaning out of data by using a
hierarchy of multiple layers that mimic the neural networks of our brain.
If you provide the system tons of information, it begins to understand it and
respond in useful ways.
3/12
6. Deep Learning - Basics
ML vs DL
6/12
ML DL
High-Performance
Computing
No Yes
Training dataset Small Large
Choose your own
features
Yes No
# of classifiers
available
Many Few
Training Time Short Long
• What to choose ?
7. Deep Learning – Application
ANNs - Artificial Neural Networks
Biological neural networks ANNs or Artificial neural networks
7/12
8. Deep Learning – Basics
DNNs - Deep Neural Networks
DNNs is an ANN with multiple layers
between the input and output layers.
The more layers the network has, the
higher-level features it will learn.
8/12
9. Deep Learning – Basics
Architecture
A DNN consists of a hierarchy of layers,
whereby each layer transforms the
input data into more abstract
representations .
The output layer combines those
features to make predictions.
9/12
10. Deep Learning – Applications
Classes
• Convolutional Neural Nets (CNN) applied to
analysing Visual Imagery.
• Recurrent Neural Nets (RNN) applicable to tasks
such as : connected handwriting recognition,
speech recognition, Sign Language Translation.
• Image Captioning – Combining CNN and RNN
10/12
Deep learning is getting a lot of attention lately and for a good reason, it’s making a big impact in areas such as computer vision and natural language processing and in this presentation will help you understand why it becomes so popular and adresse the concepts bellow :
Frank Rosenbalt : the perceptron is an algorithm for supervised learning of binary classifiers.
Bernard Widrow, : Adaptive Linear Neuron is an early single-layer artificial neural network. golden Age
Marvin Minsky, Saymour Papert : XOR problem.
Support Vector Machine (SVM) is a supervised learning models with associated learning algorithms that analyze data used for classification and regression analysis.
It appeared since 1950s.
Human intervention is necessary to do some tasks such as feature extraction
Classification is the process of predicting the class of given data points
Classes are sometimes called as targets/ labels or categories : ML( tree decesions, knn)
You need less data in ml than deep learning.
Neurons are trained to filter and detect specific features or patterns (e.g. edge, nose) by receiving weighted input, transforming it with the activation function und passing it to the outgoing connections.
Consists of one input, one output and multiple fully-connected hidden layers in between. Each layer is represented as a series of neurons and progressively extracts higher and higher-level features of the input until the final layer essentially makes a decision about what the input shows.
Consists of one input, one output and multiple fully-connected hidden layers in between. Each layer is represented as a series of neurons and progressively extracts higher and higher-level features of the input until the final layer essentially makes a decision about what the input shows.
Consists of one input, one output and multiple fully-connected hidden layers in between. Each layer is represented as a series of neurons and progressively extracts higher and higher-level features of the input until the final layer essentially makes a decision about what the input shows.