- #1

- 2

- 1

I am just wondering if it's a

__bad__idea to attempt to learn the computational/mathematical aspects of statistical mechanics with

__zero__physics background? Maybe it's easier to learn some physics before attempting this?

You are using an out of date browser. It may not display this or other websites correctly.

You should upgrade or use an alternative browser.

You should upgrade or use an alternative browser.

- Studying
- Thread starter ANewPope23
- Start date

In summary, it is not a bad idea to learn statistics/machine learning before attempting to learn the computational/mathematical aspects of statistical mechanics. However, this should only be done after learning basic physics.f

- #1

- 2

- 1

I am just wondering if it's a

- #2

Science Advisor

Homework Helper

Gold Member

- 8,090

- 3,726

- #3

- 2

- 1

"According to Watkin et al. (1993), statistical physics tools are not only well suited to analyze existing learning algorithms but also they may suggest new approaches. In the paradigm of learning from examples (the paradigm considered in this book), examples are drawn from some unknown but fixed probability distribution and, once chosen, constitute a static quenched disorder (Watkin et al., 1993)."

"Statistical Physics and Representations in Real and Artificial Neural Networks" https://arxiv.org/abs/1709.02470

https://arxiv.org/pdf/1706.09779.pdf Ising Models and Spin Glass Models are used in machine learning.

- #4

Science Advisor

Homework Helper

Gold Member

- 8,090

- 3,726

If it is true that they are applications of deep neural networks in the field of statistical mechanics, then you may be making a mistake in trying study statistical mechanics to help you understand machine learning.

- #5

- 215

- 57

If you are interested in machine learning, you should learn machine learning.

- #6

- 3,420

- 1,208

Isn't the non-physics part of statistical mechanics just... statistics?

- #7

Science Advisor

Education Advisor

- 2,232

- 1,683

http://theoreticalminimum.com/courses/statistical-mechanics/2009/spring/lecture-2

- #8

Science Advisor

Education Advisor

- 2,232

- 1,683

- #9

Science Advisor

- 7,856

- 1,591

Isn't the non-physics part of statistical mechanics just... statistics?

If you find a text where it is, I'd like to know about it. Random variables "sample spaces" (or "probability spaces"), estimators, probability models - all familiar things when problems are presented in the context of statistics don't appear in the expositions of statistical physics that I've seen. There is traditional terminology in statistical physics that predates (and overcomes) the terminology of modern probability theory and statistics.

Share:

- Replies
- 6

- Views
- 987

- Replies
- 6

- Views
- 937

- Replies
- 6

- Views
- 1K

- Replies
- 2

- Views
- 840

- Replies
- 7

- Views
- 819

- Replies
- 5

- Views
- 844

- Replies
- 4

- Views
- 1K

- Replies
- 5

- Views
- 1K

Schools
Best non-equilibrium groups?

- Replies
- 2

- Views
- 1K

- Replies
- 4

- Views
- 1K