Help protect the Great Barrier Reef with TensorFlow on Kaggle

## TensorFlow Probability 是一个用于概率推理和统计分析的库。

```import tensorflow as tf
import tensorflow_probability as tfp

# Pretend to load synthetic data set.
features = tfp.distributions.Normal(loc=0., scale=1.).sample(int(100e3))
labels = tfp.distributions.Bernoulli(logits=1.618 * features).sample()

# Specify model.
model = tfp.glm.Bernoulli()

# Fit model given data.
coeffs, linear_response, is_converged, num_iter = tfp.glm.fit(
model_matrix=features[:, tf.newaxis],
response=tf.cast(labels, dtype=tf.float32),
model=model)
# ==> coeffs is approximately [1.618] (We're golden!)
```
TensorFlow Probability (TFP) 是一个基于 TensorFlow 构建的 Python 库，使我们能够通过该库在现代硬件（TPU、GPU）上轻松结合使用概率模型和深度学习。TFP 适合数据科学家、统计人员、机器学习研究人员，以及希望运用领域知识了解数据和做出预测的从业人员使用。TFP 包括：
• 大量可供选择的概率分布和 Bijector。
• 用于构建深度概率模型的工具，包括概率层和 `JointDistribution` 抽象。
• 变分推断和马尔可夫链蒙特卡洛方法。
• 优化器，例如 Nelder-Mead 算法、BFGS 和 SGLD。

《黑客的贝叶斯方法》(Bayesian Methods for Hackers) 是一本入门级实践教程，现在提供了 TensorFlow Probability 示例。
[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"没有我需要的信息" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"太复杂/步骤太多" },{ "type": "thumb-down", "id": "outOfDate", "label":"内容需要更新" },{ "type": "thumb-down", "id": "translationIssue", "label":"翻译问题" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"其他" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"易于理解" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"解决了我的问题" },{ "type": "thumb-up", "id": "otherUp", "label":"其他" }]