Preface
Chapter 1：Neural Networks and Gradient．Based optimization
Our iourney in this book
What iS machine Iearning?
Supervised Iearning
Unsupervised learning
Reinforcement learning
The unreaS0nabIe effectiveness of data
AIl models are wrong
Setting up your workspace
Using Kaggle kernels
Running notebooks Iocally
Installing TensorFIow
Installing Keras
Using data locally
Using the AWS deep learning AMI
Approximating functions
A forward pass
A logistic regressor
Python version of our Iogistic regressor
optimizing model parameters
Measuring modelloSS
Gradient descent
Backpropaqation
Parameter updates
Putting it all together
A deeper network
A brief introduction to Keras
lmporting Keras
A two-layer modeIin Keras
Stacking layers
Compiling the model
Training the model
Keras and TensorFIow
Tensors and the computational graph
Exercises
Summary
Chapter 2:Applying Maching Learning to Structured Data
The data
Heuristic，feature．based。and E2E models
The machine Iearning software stack
The heuristic approach
Making predictions using the heuristic model
The F1 score
Evaluating with a confusion matrix
The feature engineering approach
A feature from intuition—fraudsters don’t sleep
Expeinsight—transfer．then cash out
StatisticaI quirks—errors in balances
Preparing the data for the Keras library
One-hot encoding
Entity embeddings
Tokenizing categories
Creating input models
Training the model
Creating predictive models with Keras
Extracting the target
Creating a test set
Creating a validation set
Oversampling the training data
Building the model
Creating a simple baseline
Building more complex models
A brief primer on tree-based methods
A simple decision tree
A random forest
XGBoost
E2E modeling
Exercises
Summary
Chapter 3:Utiliziting Computer Vision
……
Chapter 4：Understanding Time Series
Chapter 5：Parising Textual Data with Natural Language
Chapter 6：Using generative Models
Chapter 7:Reinforcement Learning for Financial Markets
Chapter 8:Privacy,Debugging,and Launching Your Products
Chapter 9:Fighting Bias
Chapter 10:Bayesian Infernence and Probabilisitic
Other Books You May Enjoy
Index

本书探索了机器学习的新进展，展示了如何将其应用于包括保险、交易和贷款在内的整个金融领域。书中解释了主要机器学习技术背后的概念和算法，并提供了用于自制模型的Python代码示例。
本书基于Jannes Klaas为金融专业人士举办机器学习培训课程的经验。书中并未提供现成的金融算法，而是着重介绍了能够以多种方式应用的高级机器学习概念和思想。
书中展示了机器学习如何处理结构化数据、文本、图像和时间序，涵盖了生成对抗性学习、强化学习、调试和发布机器学习产品等方面的内容，讨论了如何克服机器学习中的偏差，最后探究了贝叶斯推理和概率编程。
你将从本书中学到：
将机器学习应用于结构化数据、自然语言、照片以及书面文本；
机器学习如何检测诈骗、预测金融趋势、分析客户情绪等；
在Python、scikit-learn、Keras和TensorFlow中实现启发式基线、时间序列、生成模型和增强学习；
深入挖掘神经网络，研究GAN和强化学习的应用；
调试机器学习应用并为上线做准备；
解决机器学习中的偏差和隐私问题。