• In 4 days, learn the most common algorithms of Deep Learning, the most popular Artificial Intelligence application today, and how Artificial Neural Networks work
• With this course, you will get one step closer to developing your own projects by learning how we can integrate Deep Learning into our lives
• This course inspired by world-renowned and best-in-class curricula, tutorials and books
• Jump-start your career by entering professional fields such as Computer Vision and Natural Language Processing with this course
• Be one step ahead in interviews with projects developed with Tensorflow, one of the world’s most popular Deep Learning libraries, included in the course

WHY TAKE THIS COURSE?

Although deep learning is a sub-branch of machine learning, it has become a profession and a field of expertise today. This is because it performs much better than conventional machine learning techniques, especially in Image processing and Natural language processing.

This course is a great introductory course that gives you an explanatory introduction to the sub-branches of Deep Learning and how neural networks work, developed and optimized, which allows you to solve more complex AI problems.

With this course, you will understand how the most promising and surprising artificial intelligence projects affect our lives and the underlying technologies. In this course, where the most popular deep learning libraries are used, you will develop projects using Python language, and you will have the skills needed to start your career in this field.

HUB

You are invited to join our Introduction to Deep Learning Hub and use this space to discuss topics related to the course, share interesting and relevant material and links, ask questions and engage with peers.

ALL OUR PROGRAMS INCLUDE

• Additional access to active mentoring by experts of the Global AI Hub 
• A joint certificate issued by Global AI Hub for each successful learner  
• The certificate you will earn in this training is valid for privileged membership applications under the CoreRelation Program

• Welcome To Introduction To Deep Learning Course!
• What is the Place of Deep Learning in the World of Artificial Intelligence?

MODULE 1

• Introduction to Artificial Intelligence
  • What is Artificial Intelligence?
  • Disambiguation in Artificial Intelligence
• Introduction to Machine Learning
  • What is Machine Learning?
  • Types of Machine Learning
  • Traditional Programming and Machine Learning
• Supervised Learning
  • What is Supervised Learning?
  • Supervised Learning Algorithms and Architectures
  • Regression and Classification
  • Machine Learning Real Life Examples
• Unsupervised Learning
  • What is Unsupervised Learning?
  • Why Do We Need Unsupervised Learning?
  • Unsupervised Learning Algorithms
• Deep Learning
  • Historical Development of Deep Learning
  • What are Artificial Neural Networks and How Do They Work?
  • Usages of Deep Learning in Daily Life
  • Why Deep Learning Has Become Popular?
  • Deep Learning vs Machine Learning
  • Tools Used in Deep Learning
  • Deep Learning Resources

MODULE 2

• Basic Regression Mathematics
  • Linear Regression
  • Logistic Regression
  • Sigmoid Activation Function
• Artificial Neural Networks and Mathematics
  • Weight, Bias, Input, Output Concepts
  • Matrix Algebra
• A Simple Perceptron Coding
  • Solution of Logic Gates with Neural Networks
  • Fahrenheit Celsius conversion
• Activation Functions
  • What is Non-linearity and Why Do We Need It?
  • ReLU, Softmax, Tanh Activation Functions
• Optimization of Neural Networks
  • Forward and Back Propagation Algorithms in Deep Learning
  • Overfitting and Underfitting
  • Regularization
  • Dropout, Early Stopping, Data Augmentation
  • Hyperparameter Optimization
• Common Optimization Algorithms
  • ADAM
  • Stochastic Gradient Descent
  • RMSPROP

MODULE 3

• Computer Vision and Image Processing
  • What is Image Processing?
  • Signal and Noise Concept
  • Computer Vision Usage Areas
  • Feature Extraction
• Convolutional Neural Networks (CNN)
  • CNN Layer Types
  • Common Activation Functions
• Pre-trained CNN Models
  • What is Pre-trained Model and What Does It Do?
  • LeNet-5
  • VGG16
  • ResNet50
• Recurrent Neural Networks (RNN)
  • What is RNN?
  • RNN and Computer Vision
• Other Techniques Used in Convolutional Networks
  • Data Augmentation
  • Transfer Learning
  • One-shot Learning
• Object Detection
  • What is Object Detection?
  • Object Detection Usage Areas
  • Object Detection Architectures
    • Faster R-CNN, YOLO, SSD
  • Object Detection Datasets
    • COCO, Pascal VOC()
• Image Classification
  • What is Image Classification?
  • Object Localization in Image
  • Image Classification Datasets
    • MNIST, ImageNet, CIFAR10
• Project: Classification of Flower Images with TensorFlow

MODULE 4

• Natural Language Processing (NLP)
  • What is Natural Language Processing?
  • Why Do We Need NLP?
  • Natural Language Processing Real-Life Uses
  • Text Data Structure and Comparison with Other Data Structures
• Text Encodings
  • Bag of Words
  • Integer Encoding
  • Word Embedding
• Recursive Neural Networks (RNN)
  • RNN Mathematics
  • Why RN?
  • Vanishing Gradient Problem
  • LSTM
  • GRU
  • Decoder – Encoder Architecture
  • Attention
  • Transformers
  • BERT
•  Project: Sentiment Analysis Workshop

EPILOGUE

• Practical Use Of What Has Been Learned
• Further Projects
• What’s Next?

LEARNING ACTIVITIES

The course includes a series of lessons that lead you through the content in small, bite-sized learning blocks. Each lesson includes exciting video sessions followed by thought-provoking assessment questions.

• Video sessions have to be marked as complete and can be accessed freely after the completion of each lesson.
• Assessment questions are graded for the calculation of certification progress.
• Each day has a “Materials” section to help you revise the topics that are seen that day.