Improve Documentation

The documentation in DJL was originally written with the expectation that users are reasonably familiar with deep learning. So, it does not go out of the way to define and explain some of the key concepts. To help users who are newer to deep learning, we created a [documentation convention](https://github.com/awslabs/djl/blob/master/docs/development/development_guideline.md#documentation-conventions) for what explanation is required to get a basic understanding of the relevant topics. We now need to update the existing javadocs to contain all the required information.

- [ ] Blocks
- [x] Convolution (and Conv1D, Conv2D, Conv3D) - @jonathan016
- [ ] Embedding Block
- [ ] Linear Block
- [ ] Activations (mostly in `Activation`)
- [ ] Prelu block
- [x] BatchNorm - @jonathan016
- [x] Dropout - @jonathan016
- [ ] Pooling (in `Pool`)
- [ ] GRU
- [ ] LSTM
- [ ] RNN
- [ ] Evaluators
- [ ] Loss Functions
- [ ] Initializers
- [ ] Optimizers
- [ ] Models
- [ ] Mlp
- [ ] ResnetV1
- [ ] SingleShotDetection
- [ ] Datasets
- [ ] Captcha
- [ ] Cifar10
- [ ] Coco
- [ ] ImageNet
- [ ] Mnist
- [ ] PikachuDetection
- [ ] StanfordMovieReview
- [ ] TatoebaEnglishFreshDataset

This issue is fairly big for a single person, so I want to set this up for multiple people to work on. Comment below if you are interested in helping with any of the documentation and which of the items above you want to work on. Also comment if you notice any other javadoc that does not match the convention. I will edit this description to keep it up to date as the documentation is updated.