Bibliography (16):

1. Deep Double Descent: Where Bigger Models and More Data Hurt

2. Deep Residual Learning for Image Recognition

3. Deep Double Descent: We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time

4. Understanding ‘Deep Double Descent’

5. Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

6. https://x.com/francoisfleuret/status/1269301689095503872

7. https://arxiv.org/pdf/2105.14368.pdf#page=18

8. Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited

9. https://windowsontheory.org/2019/12/05/deep-double-descent/

10. Reconciling modern machine learning practice and the bias-variance trade-off

11. CIFAR-10 and CIFAR-100 Datasets

12. Wikipedia Bibliography:

    1. Convolutional neural network

    2. https://en.wikipedia.org/wiki/Early_stopping  :

       https://en.wikipedia.org/wiki/Early_stopping

    3. Smoothing spline

    4. Stochastic gradient descent

    5. CIFAR-10