Enhancing Deep Learning Performance Using Displaced Rectifier Linear Unit
By David Macêdo
()
About this ebook
Related to Enhancing Deep Learning Performance Using Displaced Rectifier Linear Unit
Related ebooks
Introduction to Reliable and Secure Distributed Programming Rating: 0 out of 5 stars0 ratingsClinical Prediction Models: A Practical Approach to Development, Validation, and Updating Rating: 0 out of 5 stars0 ratingsDeep Learning for Medical Applications with Unique Data Rating: 0 out of 5 stars0 ratingsAdvanced Machine Vision Paradigms for Medical Image Analysis Rating: 0 out of 5 stars0 ratingsPython Rating: 0 out of 5 stars0 ratingsThe Diagnostic Process: Graphic Approach to Probability and Inference in Clinical Medicine Rating: 0 out of 5 stars0 ratingsInteractive Data Visualization A Complete Guide - 2020 Edition Rating: 0 out of 5 stars0 ratingsIntegration and Visualization of Gene Selection and Gene Regulatory Networks for Cancer Genome Rating: 0 out of 5 stars0 ratingsHow to Design Optimization Algorithms by Applying Natural Behavioral Patterns Rating: 0 out of 5 stars0 ratingsSoftware Modeling A Complete Guide - 2020 Edition Rating: 0 out of 5 stars0 ratingsDATA MINING and MACHINE LEARNING: CLUSTER ANALYSIS and kNN CLASSIFIERS. Examples with MATLAB Rating: 0 out of 5 stars0 ratingsComputational Learning Approaches to Data Analytics in Biomedical Applications Rating: 5 out of 5 stars5/5Advances in Computational Techniques for Biomedical Image Analysis: Methods and Applications Rating: 0 out of 5 stars0 ratingsWeb Semantics: Cutting Edge and Future Directions in Healthcare Rating: 0 out of 5 stars0 ratingsHandbook of Neural Computing Applications Rating: 5 out of 5 stars5/5Mastering Parallel Programming with R Rating: 0 out of 5 stars0 ratingsFeedforward Neural Networks: Fundamentals and Applications for The Architecture of Thinking Machines and Neural Webs Rating: 0 out of 5 stars0 ratingsA Discrete-Time Approach for system Analysis Rating: 0 out of 5 stars0 ratingsConvolutional Neural Networks: Fundamentals and Applications for Analyzing Visual Imagery Rating: 0 out of 5 stars0 ratingsTensorFlow in 1 Day: Make your own Neural Network Rating: 4 out of 5 stars4/5Multilayer Perceptron: Fundamentals and Applications for Decoding Neural Networks Rating: 0 out of 5 stars0 ratingsPerceptrons: Fundamentals and Applications for The Neural Building Block Rating: 0 out of 5 stars0 ratingsIntroduction to Deep Learning and Neural Networks with Python™: A Practical Guide Rating: 0 out of 5 stars0 ratingsNeural-Based Orthogonal Data Fitting: The EXIN Neural Networks Rating: 0 out of 5 stars0 ratingsConvolutional Neural Networks in Python: Beginner's Guide to Convolutional Neural Networks in Python Rating: 0 out of 5 stars0 ratingsLong Short Term Memory: Fundamentals and Applications for Sequence Prediction Rating: 0 out of 5 stars0 ratingsFuzzy Logic and Expert Systems Applications Rating: 5 out of 5 stars5/5General Dynamical Processes: A Mathematical Introduction Rating: 0 out of 5 stars0 ratingsBio Inspired Computing: Fundamentals and Applications for Biological Inspiration in the Digital World Rating: 0 out of 5 stars0 ratings
Intelligence (AI) & Semantics For You
ChatGPT For Fiction Writing: AI for Authors Rating: 5 out of 5 stars5/5Artificial Intelligence: A Guide for Thinking Humans Rating: 4 out of 5 stars4/52084: Artificial Intelligence and the Future of Humanity Rating: 4 out of 5 stars4/5101 Midjourney Prompt Secrets Rating: 3 out of 5 stars3/5Summary of Super-Intelligence From Nick Bostrom Rating: 5 out of 5 stars5/5Our Final Invention: Artificial Intelligence and the End of the Human Era Rating: 4 out of 5 stars4/5The Secrets of ChatGPT Prompt Engineering for Non-Developers Rating: 5 out of 5 stars5/5Mastering ChatGPT: 21 Prompts Templates for Effortless Writing Rating: 5 out of 5 stars5/5Chat-GPT Income Ideas: Pioneering Monetization Concepts Utilizing Conversational AI for Profitable Ventures Rating: 4 out of 5 stars4/5Creating Online Courses with ChatGPT | A Step-by-Step Guide with Prompt Templates Rating: 4 out of 5 stars4/5Dark Aeon: Transhumanism and the War Against Humanity Rating: 5 out of 5 stars5/5Discovery Writing with ChatGPT: AI-Powered Storytelling: Three Story Method, #6 Rating: 0 out of 5 stars0 ratingsImpromptu: Amplifying Our Humanity Through AI Rating: 5 out of 5 stars5/5ChatGPT For Dummies Rating: 0 out of 5 stars0 ratingsMidjourney Mastery - The Ultimate Handbook of Prompts Rating: 5 out of 5 stars5/5Ways of Being: Animals, Plants, Machines: The Search for a Planetary Intelligence Rating: 4 out of 5 stars4/5What Makes Us Human: An Artificial Intelligence Answers Life's Biggest Questions Rating: 5 out of 5 stars5/5The Algorithm of the Universe (A New Perspective to Cognitive AI) Rating: 5 out of 5 stars5/5THE CHATGPT MILLIONAIRE'S HANDBOOK: UNLOCKING WEALTH THROUGH AI AUTOMATION Rating: 5 out of 5 stars5/5AI for Educators: AI for Educators Rating: 5 out of 5 stars5/5ChatGPT Ultimate User Guide - How to Make Money Online Faster and More Precise Using AI Technology Rating: 0 out of 5 stars0 ratingsThe Business Case for AI: A Leader's Guide to AI Strategies, Best Practices & Real-World Applications Rating: 0 out of 5 stars0 ratingsHumans Need Not Apply: A Guide to Wealth & Work in the Age of Artificial Intelligence Rating: 4 out of 5 stars4/5
Reviews for Enhancing Deep Learning Performance Using Displaced Rectifier Linear Unit
0 ratings0 reviews
Book preview
Enhancing Deep Learning Performance Using Displaced Rectifier Linear Unit - David Macêdo
To my family.
Acknowledgements
This work would not have been possible without the support of many. I would like to thank and dedicate this dissertation to the following people:
To my advisor Teresa Ludermir. Teresa is an exceptional researcher and professor. Her guidance and support were fundamental to motivate me throughout this research.
To my co-advisor Cleber Zanchettin for his contributions to the work we have done.
To my family, especially my parents, José and Mary, my wife Janaina, and my children, Jéssica, and Daniel, for give me the love that I need through my whole life.
Things should be made as simple as possible, but no simpler.
—ALBERT EINSTEIN
List of Acronyms
Contents
Capa
Folha de Rosto
Créditos
1. Introduction
1.1 CONTEXT
1.2 PROBLEM
1.3 GOAL
1.4 OUTLINE
2. Background
2.1 DEEP LEARNING
2.2 ACTIVATION FUNCTIONS
2.2.1 Rectifier Linear Unit
2.2.2 Leaky Rectifier Linear Unit
2.2.3 Parametric Rectifier Linear Unit
2.2.4 Exponential Linear Unit
2.3 CONVOLUTIONAL NETWORKS
2.4 ARCHITECTURES
2.4.1 Visual Geometry Group
2.4.2 Residual Networks
2.5 REGULARIZATION
2.5.1 Dropout
2.5.2 Batch Normalization
3. Displaced Rectifier Linear Unit
4. Experiments
4.1 DATASETS, PREPROCESSING AND DATA AUGMENTATION
4.2 ACTIVATION FUNCTIONS PARAMETRIZATION
4.3 MODELS AND INITIALIZATION
4.4 TRAINING AND REGULARIZATION
4.5 PERFORMANCE ASSESSMENT
5. Results
5.1 BIAS SHIFT EFFECT
5.2 CIFAR-10 DATASET
5.2.1 VGG-19 Model
5.2.2 ResNet-56 Model
5.2.3 ResNet-110 Model
5.3 CIFAR-100 DATASET
5.3.1 VGG-19 Model
5.3.2 ResNet-56 Model
5.3.3 ResNet-110 Model
5.4 DISCUSSION
6. Conclusion
6.1 CONTRIBUTIONS
6.2 FUTURE WORK
References
Landmarks
cover
title-page
copyright-page
table of contents
Bibliografia
1. Introduction
A journey of a thousand miles begins with a single step.
—LAO TZU
In this introductory chapter, we explain the context of this work, which is deep learning research. After that, we establish the problem of interest. Then we set the goals of this study and the contributions we achieved. Finally, we present an outline of the subject of the next chapters.
1.1 CONTEXT
The artificial neural networks research passed through three historical waves (Fig.1.1) (GOODFELLOW; BENGIO; COURVILLE,2016). The first one, known as cybernetics, started at the 1960s with the work of Rosenblatt and the definition of the Perceptron, which was showed to be useful in linear separable problems (ROSENBLATT,1958). This initial excitement diminished in the 1970s by the work of Minsk and Papert (MINSKY; PAPERT,1969), which demonstrated some limitations of this concept.
The second wave of artificial neural networks research, known as connectionism, began in the 1980s after the dissemination of the discovery of the so-called backpropagation algorithm (RUMELHART; HINTON; WILLIAMS,1986), which allowed training neural networks with few hidden layers. Nevertheless, the Vanish Gradient Problem supported the idea that training neural networks with more than few layers was a hard challenge (HOCHREITER,1991).
Therefore, this second wave was replaced by a huge interest in new statistical machine learning methods discovered or improved in the 1990s. Artificial neural networks research passed through another dismal period and fell out of favor again. Indeed, it was a time when the machine learning researchers largely forsook neural networks and backpropagation was ignored by the computer vision and natural language processing communities.
Figure 1.1: The three historical waves of artificial neural networks research (GOODFELLOW; BENGIO; COURVILLE,2016).
The third and present wave of artificial neural networks research has been called deep learning, and it started at the late 2000s with some seminal works from Geoffrey Hinton, Yoshua Bengio, and Yann LeCun, which showed that it is possible to train artificial neural networks with many hidden layers. The recent advances in deep learning research have produced more accurate image, speech, and language recognition systems and have generated new state-of- the-art machine learning applications in a broad range of areas such as mathematics, physics, healthcare, genomics, financing, business, agriculture, etc.
Activation functions are the components of neural networks architectures responsible for adding nonlinearity capabilities to the models. In fact, considering Figure1.2, the transformation performed by a generic shallow or deep neural network layer can be written bellow:
As can be seen in Eq.1.1, the activation function is the only component of a neural network, or a deep architecture, that incorporates nonlinearity capability. Indeed, if the activation function f is removed from the mentioned equation, a particular layer would be