TODO List for 0.1 release

### Base Classes
- [x] [nn::Module](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [x] [autograd::Variable](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [x] [Solver](https://github.com/arrayfire/arrayfire-ml/issues/35)
- [x] [nn::Loss](https://github.com/arrayfire/arrayfire-ml/issues/34)

### Autograd
- [x] Broadcasting [(sum, tile)](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [x] [Math](https://github.com/arrayfire/arrayfire-ml/pull/30) (exp, pow, abs, sqrt, log)
- [x] Binary ([add, subtract, multiply, divide](https://github.com/arrayfire/arrayfire-ml/pull/30), [min, max, logical operators](https://github.com/arrayfire/arrayfire-ml/pull/32))
- [x] [matrix multiplication](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [ ] [Convolutions and strided Convolutions](https://github.com/arrayfire/arrayfire-ml/issues/33)
- [ ] [Indexing and assignment](https://github.com/arrayfire/arrayfire-ml/issues/43)

### Neural Network
- [x] [Linear](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [ ] [Convolve](https://github.com/arrayfire/arrayfire-ml/issues/33)
- [ ] [Pooling (Min, Max, Average)](https://github.com/arrayfire/arrayfire-ml/issues/33)
- [x] Activations: [Sigmoid, Tanh](https://github.com/arrayfire/arrayfire-ml/pull/30), [ReLU](https://github.com/arrayfire/arrayfire-ml/pull/31) and [related](https://github.com/arrayfire/arrayfire-ml/pull/32)
- [ ] [Recurrent neural networks (RNN, LSTM, GRU)](https://github.com/arrayfire/arrayfire-ml/issues/20)
- [ ] [Various Losses](https://github.com/arrayfire/arrayfire-ml/issues/34)
- [x] [Containers (Sequential)](https://github.com/arrayfire/arrayfire-ml/pull/30)
- [x] [Initializers](https://github.com/arrayfire/arrayfire-ml/issues/24)

### Solvers / Optimizers
- [x] [SGD](https://github.com/arrayfire/arrayfire-ml/issues/35)
- [x] [ADAM](https://github.com/arrayfire/arrayfire-ml/issues/35)

### Examples

Start by reviewing the unchecked linked issues for convolutions, indexing and assignment, recurrent neural networks, and various losses. The checklist spans multiple neural-network and autograd components, so confirm which items remain relevant before choosing a focused task. Done would require completing the agreed remaining work for the 0.1 release.

Scritto dal modello di indicizzazione a partire dal testo della issue.