The Next Journey: Which Book to Read Together?
Opened this issue · 4 comments
Neuroscience + Machine Learning
我觉得可以学习一下结合 neuroscience + machine learning 这样的书。如果讨论类型的话,大致有:
- Application of machine learning in neuroscience
- Application of neuroscience in machine learning:neuroscience inspired hardware/software and how can we go furthure.
- Machine learning for neuroscientists:单纯的学习 machine learning,这是另一个读书会的主题,所以这里应该不考虑。
找到一篇论文 Toward an Integration of Deep Learning and Neuroscience
还有一本有意思的书:Emergent Neural Computational Architectures Based on Neuroscience
Computational Neuroscience
如果单纯这个的话,似乎可以进一步学习一下 theoretical neuroscience, 例如
Theoretical Neuroscience
Computational and Mathematical Modeling of Neural Systems
by Peter Dayan and LF Abbott
这本书里面也有关于 neuroscience 和 machine learning 的讨论。(G. Hinton 的短文 Machine learning for neuroscience 推荐的一本书,提到里面有非常有趣的关于大脑和 machine learning 的观点。)
目录:
Contents
Preface
Part I: Neural Encoding and Decoding
1 Neural encoding I: Firing rates and spike statistics
2 Neural encoding II: Reverse correlation and visual receptive fields
3 Neural decoding
4 Information theory
Part II: Neurons and Neural Circuits
5 Model neurons I: Neuroelectronics
6 Model neurons II: Conductances and morphology
7 Network models
Part III: Adaptation and Learning
8 Plasticity and learning
9 Classical conditioning and reinforcement learing
10 Representational learning
Mathematical appendix
References
https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers 。 这本既有一些模型的内容也侧重相关的编程。而且有一些ipython notebook 的例子。 书目如下。
Prologue: Why we do it.
Chapter 1: Introduction to Bayesian Methods Introduction to the philosophy and practice of Bayesian methods and answering the question, "What is probabilistic programming?"
Chapter 2: A little more on PyMC We explore modeling Bayesian problems using Python's PyMC library through examples. How do we create Bayesian models?
Chapter 3: Opening the Black Box of MCMC We discuss how MCMC, Markov Chain Monte Carlo, operates and diagnostic tools.
Chapter 4: The Greatest Theorem Never Told We explore an incredibly useful, and dangerous, theorem: The Law of Large Numbers.
Chapter 5: Would you rather lose an arm or a leg? The introduction of loss functions and their (awesome) use in Bayesian methods.
Chapter 6: Getting our prior-ities straight Probably the most important chapter. We examine our prior choices and draw on expert opinions craft priors.
Chapter X1: Bayesian methods in Machine Learning and Model Validation We explore how to resolve the overfitting problem plus popular ML methods.
Chapter X2: More PyMC Hackery We explore the gritty details of PyMC.
我推荐这本 The Elements of Statistical Learning
https://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf
这是目录
- Introduction
- Overview of Supervised Learning
- Linear Methods for Regression
- Linear Methods for Classification
- Basis Expansions and Regularization
- Kernel Smoothing Methods
- Model Assessment and Selection
- Model Inference and Averaging
- Additive Models, Trees, and Related Methods
- Boosting and Additive Trees
- Neural Networks
- Support Vector Machines and Flexible Discriminants
- Prototype Methods and Nearest-Neighbors
- Unsupervised Learning
- Random Forests
- Ensemble Learning
- Undirected Graphical Model
- High-Dimensional Problems
我是觉得很多感兴趣的点都涵盖了,全书刷下来肯定会有帮助