CNN

For my assignment, I was training a 1D CNN model to predict stock prices. Whilst most of the models gave 0.5% accuracy, there was one version of the model trained with a learning rate of 1e-3 that was giving me 80% accuracy. I am a little skeptical. It feels a little too good to be true. A model that gave 0.8% accuracy would mean that this model would be extremely profitable. Sounds a litle too good to be true? ...

Learnings: Using Alexnet model with kernel settings of size=11, stride=4, padding=2, and image size of 227x227, I could reach 70% accuracy with training of 30 epochs. This, unfortunately, is the same level of accuracy as my Simplenet in the previous post Training Using a simple neural network from the previous post, I could reach an accuracy level of 0.7. However whilst implementing the following CNN from chapter 3 of the Pytorch book, I realized that I had quite a few issues trying to get it to converge. ...