03990nam a22005655i 4500 978-981-97-2720-9 DE-He213 20251030112034.0 cr nn 008mamaa 240509s2024 si | s |||| 0|eng d 9789819727209 978-981-97-2720-9 10.1007/978-981-97-2720-9 doi Q342 UYQ bicssc COM004000 bisacsh UYQ thema Santosh, KC. author. aut http://id.loc.gov/vocabulary/relators/aut Cracking the Machine Learning Code: Technicality or Innovation? [electronic resource] / by KC Santosh, Rodrigue Rizk, Siddhi K. Bajracharya. 1st ed. 2024. Singapore : Springer Nature Singapore : Imprint: Springer, 2024. XIX, 127 p. 110 illus., 103 illus. in color. online resource. text txt rdacontent computer c rdamedia online resource cr rdacarrier text file PDF rda Studies in Computational Intelligence, 1860-9503 ; 1155 Chapter 1. Introduction -- Chapter 2. Data modalities and preprocessing -- Chapter 3. Basic building blocks: From shallow to deep -- Chapter 4. Experimental Setup -- Chapter 5: Case study: from numbers to images -- Chapter 6: Extension: Multimodal learning representation -- Chapter 7. Where is the innovation?. Employing off-the-shelf machine learning models is not an innovation. The journey through technicalities and innovation in the machine learning field is ongoing, and we hope this book serves as a compass, guiding the readers through the evolving landscape of artificial intelligence. It typically includes model selection, parameter tuning and optimization, use of pre-trained models and transfer learning, right use of limited data, model interpretability and explainability, feature engineering and autoML robustness and security, and computational cost – efficiency and scalability. Innovation in building machine learning models involves a continuous cycle of exploration, experimentation, and improvement, with a focus on pushing the boundaries of what is achievable while considering ethical implications and real-world applicability. The book is aimed at providing a clear guidance that one should not be limited to building pre-trained models to solve problems using the off-the-self basic building blocks. With primarily three different data types: numerical, textual, and image data, we offer practical applications such as predictive analysis for finance and housing, text mining from media/news, and abnormality screening for medical imaging informatics. To facilitate comprehension and reproducibility, authors offer GitHub source code encompassing fundamental components and advanced machine learning tools. Computational intelligence. 64052 Machine learning. 55059 Artificial intelligence Data processing. Computational Intelligence. 64052 Machine Learning. 55059 Data Science. Rizk, Rodrigue. author. aut http://id.loc.gov/vocabulary/relators/aut 76591 Bajracharya, Siddhi K. author. aut http://id.loc.gov/vocabulary/relators/aut 76592 SpringerLink (Online service) Springer Nature eBook Printed edition: 9789819727193 Printed edition: 9789819727216 Printed edition: 9789819727223 Studies in Computational Intelligence, 1860-9503 ; 1155 68854 https://doi.org/10.1007/978-981-97-2720-9 ZDB-2-INR ZDB-2-SXIT 59746 59746