Book Image

The Deep Learning Architect's Handbook

By : Ee Kin Chin
5 (1)
Book Image

The Deep Learning Architect's Handbook

5 (1)
By: Ee Kin Chin

Overview of this book

Deep learning enables previously unattainable feats in automation, but extracting real-world business value from it is a daunting task. This book will teach you how to build complex deep learning models and gain intuition for structuring your data to accomplish your deep learning objectives. This deep learning book explores every aspect of the deep learning life cycle, from planning and data preparation to model deployment and governance, using real-world scenarios that will take you through creating, deploying, and managing advanced solutions. You’ll also learn how to work with image, audio, text, and video data using deep learning architectures, as well as optimize and evaluate your deep learning models objectively to address issues such as bias, fairness, adversarial attacks, and model transparency. As you progress, you’ll harness the power of AI platforms to streamline the deep learning life cycle and leverage Python libraries and frameworks such as PyTorch, ONNX, Catalyst, MLFlow, Captum, Nvidia Triton, Prometheus, and Grafana to execute efficient deep learning architectures, optimize model performance, and streamline the deployment processes. You’ll also discover the transformative potential of large language models (LLMs) for a wide array of applications. By the end of this book, you'll have mastered deep learning techniques to unlock its full potential for your endeavors.
Table of Contents (25 chapters)
1
Part 1 – Foundational Methods
11
Part 2 – Multimodal Model Insights
17
Part 3 – DLOps

Exploring Bias and Fairness

A biased machine learning model produces and amplifies unfair or discriminatory predictions against certain groups. Such models can produce biased predictions that lead to negative consequences such as social or economic inequality. Fortunately, some countries have discrimination and equality laws that protect minority groups against unfavorable treatment. One of the worst scenarios a machine learning practitioner or anyone who deploys a biased model could face is either receiving a legal notice imposing a heavy fine or receiving a lawyer letter from being sued and forced to shut down their deployed model. Here are a few examples of such situations:

  • The ride-hailing app Uber faced legal action from two unions in the UK for its facial verification system, which showed racial bias against dark-skinned people by displaying more frequent verification errors. This impeded their work as Uber drivers (https://www.bbc.com/news/technology-58831373).
  • Creators...