Hey community, hope you can help me with some of the fundamental concepts in NN
My understanding of NN is,
- NN is one giant multi-dimensional loss function with the loss on one axis and the weights on the other axes
- Initially, the weights are assigned random values
- When you train a model what is essentially happening is each input (eg. image), from the training set, is processed through a funnel of different arrays of weights from the loss function (I am guessing these arrays are filters), to get to a prediction.
- Layers in the NN are a way to group filters (array of weights)
- The prediction on an input is checked against the true value of that input to calculate the loss for a given set of weights
- SGD technique is being used to navigate the loss function to arrive at a loss value that is lower than the previous loss value for a given set of weights, this is how weights are tuned.
Hope I am on the right track here
Based on my understanding, I am trying to figure out the following,
- What is this giant multi-dimensional loss function?
- What are the filters? Are they indeed just arrays of weights defined in the loss function? How are these arrays created?