Tensorised deep learning models compress large models using fewer parameters that are easier to express and explain the models' performance. To use and participate in the current state-of-the-art research of multi-way analysis using tensor structures and algebra, a foundation in some mathematical concepts using examples and visualisations is required. This book covers the link from theoretical foundations to example applications in machine learning and deep neural network models. Plenty of Python libraries and application examples are referenced and explained to make it easier for newcomers in the field. All required prerequisites are referenced for a deeper foundation from scratch.
Tensorised deep learning models compress large models using fewer parameters that are easier to express and explain the models' performance. To use and participate in the current state-of-the-art research of multi-way analysis using tensor structures and algebra, a foundation in some mathematical concepts using examples and visualisations is required. This book covers the link from theoretical foundations to example applications in machine learning and deep neural network models. Plenty of Python libraries and application examples are referenced and explained to make it easier for newcomers in the field. All required prerequisites are referenced for a deeper foundation from scratch.
Introduction to Tensor Computing in Python: From First Principles to Deep Learning
240
Introduction to Tensor Computing in Python: From First Principles to Deep Learning
240
Product Details
| ISBN-13: | 9781916626331 |
|---|---|
| Publisher: | Manal Helal |
| Publication date: | 05/11/2023 |
| Pages: | 240 |
| Product dimensions: | 8.50(w) x 11.00(h) x 0.51(d) |