Chapter 3: ResNets, inception networks and other variants
Chapter Goal: Describe what resnet, alexnet, inception networks are and their application
No of pages: 30-50
Sub -Topics
1. ResNets introduction, development, etc.
2. Inception networks
3. Other architectures
Chapter 4: More advanced networks
Chapter Goal: Describe the problem of more advanced algorithms, like siamese networks, triplet loss, neural style transfer
No of pages: 50-70
Sub -Topics
1. Siamese networks
2. Neural style transfer
3. Different cost functions: style, content and cost
Chapter 5: Medical example with CNN (Cancer example) in collaboration with 4quant probably
Chapter Goal: Develop a cancer diagnosis CNN with a real dataset in collaboration with 4quant
No of pages: 30-50
Sub -Topics
1. 4quant description
2. Problem description
3. Dataset preparation and discussion
4. Network development
5. Optimization
6. Results
Chapter 6: Recurrent Neural Networks – an introduction
Chapter Goal: explain what Recurrent neural networks are
No of pages: 30-50
Sub -Topics
1. Recurrent neural networks
2. Time component in RNN
3. Different types of RNN
4. LSTM Networks
Chapter 7: LSTM Networks – a more advanced discussion
Chapter Goal: Discuss in more details LSTM Networks
No of pages: 50-60
Sub -Topics
1. Overview of LSTM networks
2. The mathematics behind them
3. A practical application
Chapter 8: Recurrent Neural Networks and language
Chapter Goal: Introduction on how to use RNN and language problem
No of pages: 30-50
Sub -Topics
1. Word embeddings and the problem of language modelling
2. Word2vec
3. A practical example
Chapter 9: Sequence to sequence architecture
Chapter Goal: Introduce sequence to sequence architectures
No of pages: 30-50
Sub -Topics
1. Introduction to the architecture
2. Practical implementation tips
3. Real use case application
Chapter 10: A practical complete example: Speech recognition
Chapter Goal: in this chapter I will put together all that was explained before and do a real-life example ML project (with all aspects included) about speech recognition
No of pages: 30-50
Sub -Topics
1. A complete example on speech recognition – an introduction
2. Dataset discussion
3. Dataset preparation
4. The implementation
Umberto Michelucci studied physics and mathematics. He is an expert in numerical simulation, statistics, data science, and machine learning. In addition to several years of research experience at the George Washington University (USA) and the University of Augsburg (DE), he has 15 years of practical experience in the fields of data warehouse, data science, and machine learning. His last book Applied Deep Learning – A Case-Based Approach to Understanding Deep Neural Networks was published by Apress in 2018. He is very active in research in the field of artificial intelligence and publishes his research results regularly in leading journals and gives regular talks at international conferences.
He teaches as a lecturer at the Zurich University of Applied Sciences and at the HWZ University of Applied Sciences in Business Administration. He is also responsible for AI, research, and new technologies at Helsana Vesicherung AG.
He recently founded TOELT LLC, a company aiming to develop new and modern teaching, coaching, and research methods for AI, to make AI technologies and research accessible to everyone.
Develop and optimize deep learning models with advanced architectures. This book teaches you the intricate details and subtleties of the algorithms that are at the core of convolutional neural networks. In Advanced Applied Deep Learning, you will study advanced topics on CNN and object detection using Keras and TensorFlow.
Along the way, you will look at the fundamental operations in CNN, such as convolution and pooling, and then look at more advanced architectures such as inception networks, resnets, and many more. While the book discusses theoretical topics, you will discover how to work efficiently with Keras with many tricks and tips, including how to customize logging in Keras with custom callback classes, what is eager execution, and how to use it in your models.
Finally, you will study how object detection works, and build a complete implementation of the YOLO (you only look once) algorithm in Keras and TensorFlow. By the end of the book you will have implemented various models in Keras and learned many advanced tricks that will bring your skills to the next level.
You will:
See how convolutional neural networks and object detection work
Save weights and models on disk
Pause training and restart it at a later stage
Use hardware acceleration (GPUs) in your code
Work with the Dataset TensorFlow abstraction and use pre-trained models and transfer learning
Remove and add layers to pre-trained networks to adapt them to your specific project
Apply pre-trained models such as Alexnet and VGG16 to new datasets