Any good math-theory-focused books on neural networks and data science?

In summary, there are several books available on the topic of data science with a focus on neural networks and mathematical rigor. Some examples include "Algorithms for Optimization" by Kochenderfer, "The 100 Page Machine Learning Book" by Burkov, and "Hands-on ML with Scikit-Learn, Keras and Tensorflow" by Geron. However, while these books do discuss the math behind machine learning, they may not meet the level of rigor you are looking for. In terms of papers, there are also several available on topics such as function approximation, gradient descent effectiveness, and error estimation.
  • #1
s00mb
33
10
Hi. I'm looking for books on data science, preferably leaning towards neural networks, that focus on mathematical rigor. For example, theorems on optimization, minimum number of layers to accomplish a task efficiently, etc. Most books I've seen seem to hand wave this stuff. Anyone know any juicy books on the topic?
 
Physics news on Phys.org
  • #2
There's a rather recent book by Kochenderfer called Algorithms for Optimization with many examples written in Julia, a hot programming language from MIT that folks are using for numerical work in diverse fields including ML and Data Science.

https://www.amazon.com/dp/0262039427/?tag=pfamazon01-20

There's also the 100 page ML book by Burkov:

https://www.amazon.com/dp/199957950X/?tag=pfamazon01-20

which is available online as a try and buy book.

Lastly, Geron's book Hands-on ML with Scikit-Learn, Keras and Tensorflow:

https://www.amazon.com/dp/1492032646/?tag=pfamazon01-20

All are good books that discuss the math behind the ML although not at the rigor you're looking for.
 
  • #3
I looked through "Data mining" by Witten, Frank, Hall and, Pal which covers most of these, but it isn't rigorous like the good old math analysis books. No wonder for such a rapidly developing (practical) area.
 

Related to Any good math-theory-focused books on neural networks and data science?

1. What are some good introductory books on neural networks and data science?

Some popular introductory books on these topics include "Neural Networks and Deep Learning" by Michael Nielsen, "Data Science from Scratch" by Joel Grus, and "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.

2. Are there any books that focus specifically on the math and theory behind neural networks?

Yes, "Neural Networks and Learning Machines" by Simon Haykin and "Deep Learning" by Yoshua Bengio, Ian Goodfellow, and Aaron Courville both delve into the mathematical foundations of neural networks.

3. Are there any books that cover both neural networks and data science together?

Yes, "Neural Networks for Data Science" by Sebastian Raschka and Vahid Mirjalili and "Data Science and Machine Learning: Mathematical and Statistical Methods" by Dirk Kroese, Joshua Chan, and Thomas Taimre both cover both topics in depth.

4. Are there any books that are suitable for both beginners and advanced readers?

Yes, "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow" by Aurélien Géron and "Deep Learning with Python" by François Chollet are both comprehensive books that cover both introductory and advanced concepts in neural networks and data science.

5. Are there any books that focus specifically on the application of neural networks in real-world scenarios?

Yes, "Applied Predictive Modeling" by Max Kuhn and Kjell Johnson and "Data Science for Business" by Foster Provost and Tom Fawcett both cover the application of neural networks and data science in various industries and use cases.

Similar threads

  • Science and Math Textbooks
Replies
2
Views
949
  • MATLAB, Maple, Mathematica, LaTeX
Replies
1
Views
1K
Replies
13
Views
1K
  • STEM Academic Advising
Replies
4
Views
2K
  • Science and Math Textbooks
Replies
5
Views
5K
  • Science and Math Textbooks
2
Replies
38
Views
6K
  • Science and Math Textbooks
Replies
26
Views
7K
Replies
1
Views
470
Replies
10
Views
2K
Replies
17
Views
2K
Back
Top