neural networks and deep learning-chapter1-3
使用梯度下降算法進行學習 現在我們有了一個神經網絡，接下來我們需要的就是一個訓練數據集。該書採用的是 MNIST 數據集。 我們希望能夠找到合適的一組權重及偏置，使得數據能夠全部被正確地分類。爲了量化我們與這個目標的距離，我們定義一個代價函數(也被稱爲損失函數或目標函數)： 
相關文章
- 1. Neural Networks and Deep Learning -- Class 4: Deep Neural Networks
- 2. Neural Networks and Deep Learning
- 3. Neural Networks and Deep Learning -- Class 3: Shallow neural networks
- 4. neural networks and deep learning-chapter1-2
- 5. COURSE 1 Neural Networks and Deep Learning
- 6. Neural Networks and Deep Learning-引論
- 7. Neural Networks and Deep Learning_week3練習
- 8. Neural Networks and Deep Learning_week2練習
- 9. Neural Networks and Deep Learning（week4）深層神經網絡（Deep Neural Networks）
- 10. Neural Networks and Deep Learning -- Class 2: Neural Network Basics