课程一(Neural Networks and Deep Learning)，第二周（Basics of Neural Network programming）—

1. Build a logistic regression model, structured as a shallow neural network
2. Implement the main steps of an ML algorithm, including making predictions, derivative computation, and gradient descent.
3. Implement computationally efficient, highly vectorized, versions of models.
4. Understand how to compute derivatives for logistic regression, using a backpropagation mindset.
5. Become familiar with Python and Numpy
6. Work with iPython Notebooks
7. Be able to implement vectorization across multiple training examples

----------------------------------------------中文翻译---------------------------------------------------------------

1. 构建一个逻辑回归模型, 构造成一个浅层神经网络

2. 实现 ML 算法的主要步骤, 包括进行预测、导数计算和梯度下降。

3. 实现计算效率高、高度向量化的模型版本。

4. 理解如何用反向传播的思维来计算逻辑回归的导数。

5. 熟悉 Python 和 Numpy

6. 使用 iPython Notebooks

7. 能够在多个训练样本中实现向量化

巴特西

课程一(Neural Networks and Deep Learning)，第二周（Basics of Neural Network programming）—— 0、学习目标

最新文章

热门文章