Machine Learning and Artificial Intelligence: Trends and Applications

Deep Learning, Generative Models, and Real-World Deployments

Edited by: Marcus Lindqvist · Chen Wei

ISBN: 978-1-83568-134-3 DOI: 10.12345/csit.mlai.2023 Published: September 2023

Submit a Paper Browse Papers

Papers

Type

Edited Book

ISBN

978-1-83568-134-3

DOI

10.12345/csit.mlai.2023

Published

Sep 2023

About this Book

This volume provides an in-depth exploration of the rapidly evolving landscape of machine learning and AI. Chapters cover transformer architectures, large language models, computer vision, reinforcement learning, and responsible AI practices. Written by leading researchers from top institutions worldwide, the book is essential reading for both researchers and practitioners.

Editors

Marcus Lindqvist · KTH Royal Institute of Technology, Stockholm
Chen Wei · Tsinghua University

Publication Details

Series: Computer Science and Information Technology Series
Type: Edited Book
ISBN: 978-1-83568-134-3
DOI: 10.12345/csit.mlai.2023
Year: 2023
Published: 10 Sep 2023

📋

Submit a Camera-Ready Paper

This book is accepting camera-ready paper submissions. Submit your research to be included in this publication.

Submit Your Paper →

01 vision transformer medical image segmentation deep learning

Vision Transformers for Medical Image Segmentation: A Comprehensive Survey

Chen Wei*, Xia Liu * corresponding author

This survey provides a thorough examination of Vision Transformer (ViT) architectures applied to medical image segmentation tasks. We review over 120 recent publications covering fundus photography, CT scan analysis, MRI brain segmentation, and histopathology slide processing. We identify key architectural innovations, benchmark datasets, and open research challenges.

Abstract This survey provides a thorough examination of Vision Transformer (ViT) architectures applied to medical image segmentation tasks. We review over 120 recent publications covering fundus photography, CT scan analysis, MRI brain segmentation, and histopathology slide processing. We identify key architectural innovations, benchmark datasets, and open research challenges.

02 large language models code generation GPT

Large Language Models in Code Generation: Capabilities, Limits, and Safety

Chen Wei* * corresponding author

We systematically evaluate large language models (LLMs) for automated code generation across multiple programming languages and task types. Our study assesses functional correctness, security vulnerabilities, and alignment with developer intent using a novel benchmark suite. We discuss prompt engineering strategies that improve generation quality and safety filtering mechanisms.

Abstract We systematically evaluate large language models (LLMs) for automated code generation across multiple programming languages and task types. Our study assesses functional correctness, security vulnerabilities, and alignment with developer intent using a novel benchmark suite. We discuss prompt engineering strategies that improve generation quality and safety filtering mechanisms.

03 federated learning differential privacy healthcare

Federated Learning for Privacy-Preserving Healthcare Analytics

Chen Wei*, James Okonkwo * corresponding author

Federated learning enables collaborative model training across distributed healthcare institutions without sharing patient data. This chapter presents a privacy-preserving federated framework with differential privacy guarantees, secure aggregation protocols, and personalization mechanisms for non-IID healthcare datasets. Experiments on electronic health records demonstrate superior performance over baseline approaches.

Abstract Federated learning enables collaborative model training across distributed healthcare institutions without sharing patient data. This chapter presents a privacy-preserving federated framework with differential privacy guarantees, secure aggregation protocols, and personalization mechanisms for non-IID healthcare datasets. Experiments on electronic health records demonstrate superior performance over baseline approaches.

Book Information

Series: Computer Science and Information Technology Series
Type: Edited Book
ISBN: 978-1-83568-134-3
DOI: 10.12345/csit.mlai.2023
Year: 2023
Published: 10 Sep 2023
Papers: 3
Language: English

Publish in this Book

Submit your camera-ready paper to be included in this publication.

Submit a Paper

More in this Series

CL Cloud Computing, Edge Intelligence, and Distributed Sys... (2022) CY Cybersecurity in the Digital Age (2023)

View all books in series →