Deep Learning Hardware: CPU and GPU Hands-on Deep Learning v2

1. Deep Learning Hardware: CPU and GPU

2. Q & A

• 1. With more data, generalization can be improved.
• 2. AlexNet uses a fully connected layer, and ResNet is smaller than AlexNet; but ResNet has a larger computational load than AlexNet.
• 3. For deep neural networks, adding layers is also a hyperparameter.
• 4. The development of hardware follows Moore's Law, and the amount of calculation is exponential in the early stage. The corresponding growth time, the complexity diagram is as follows.
     

reference

https://www.bilibili.com/video/BV1TU4y1j7Wd/?spm_id_from=trigger_reload