[WIP] add docstrings and doc improvements

docs/src/training/optimisers.md

@@ -59,18 +59,20 @@ An optimiser takes a parameter list and returns a function that does the same th
 
 All optimisers return a `struct` that, when called with their `update!`, will update the parameters passed to it.
 
-```@docs
+* [Descent](https://en.wikipedia.org/wiki/Stochastic_gradient_descent)
-- [Descent](https://en.wikipedia.org/wiki/Stochastic_gradient_descent)
+* [Momentum](https://arxiv.org/abs/1712.09677)
-- Momentum
+* [Nesterov](https://arxiv.org/abs/1607.01981)
-- Nesterov
+* [RMSProp](http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf)
-- RMSProp
+* [ADAM](https://arxiv.org/abs/1412.6980v8)
-- ADAM
+* [AdaMax](https://arxiv.org/abs/1412.6980v9)
-- AdaMax
+* [ADAGrad](http://www.jmlr.org/papers/volume12/duchi11a/duchi11a.pdf)
-- ADAGrad
+* [ADADelta](http://arxiv.org/abs/1212.5701)
-- ADADelta
+* [AMSGrad](https://openreview.net/forum?id=ryQu7f-RZ)
-- AMSGrad
+* [NADAM](http://cs229.stanford.edu/proj2015/054_report.pdf)
-- NADAM
+* [ADAMW](https://arxiv.org/abs/1711.05101)
-```
+* InvDecay
+* ExpDecay
+* WeightDecay
 
 ## Optimiser API
 
@@ -100,13 +102,13 @@ opt.eta = 0.2 # valid statment, useful for annealing/ scaling
 The `ExpDecay` function defined within Flux, takes advantage of this flexibility. It can be used as a way of scheduling the learning rate. It makes it easy to scale the learning rate, every `n` epochs. Additionaly, it is easy to specify a `clip` or a bound to the learning rate, beyond which it will be maintained throughout the remainder of the training.
 
 ```julia
-mutable struct ExpDecay
+ExpDecay(opt = 0.001, decay = 0.1, decay_step = 1000, clip = 1e-4)
-  eta::Float64
+```
-  decay::Float64
+
-  step::Int64
+The above would take the initial learning rate `0.001`, and decay it by `0.1` every `1000` steps until it reaches a minimum of `1e-4`. It can be used such that it can be applied on to any optimiser like so:
-  clip::Float64
+
-  current::IdDict
+```julia
-end
+Optimiser(ExpDecay(...), Descent(...))
 ```
 
 ## Optimiser

src/optimise/optimisers.jl

@@ -257,6 +257,14 @@ function update!(o::Optimiser, x, Δ)
   return Δ
 end
 
+"""
+`InvDecay(γ)`
+
+Apply inverse time decay to an optimiser
+```julia
+  Optimiser(InvDecay(..), Opt(..))
+```
+"""
 mutable struct InvDecay
   gamma::Float64
   state::IdDict
@@ -272,6 +280,16 @@ function update!(o::InvDecay, x, Δ)
   return Δ
 end
 
+"""
+`ExpDecay(eta, decay, decay_step, clip)`
+
+Schedule the learning rate `eta` by `decay` every `decay_step` till a minimum of `clip`.
+
+To apply exponential decay to an optimiser:
+```julia
+  Optimiser(ExpDecay(..), Opt(..))
+```
+"""
 mutable struct ExpDecay
   eta::Float64
   decay::Float64
@@ -292,6 +310,11 @@ function update!(o::ExpDecay, x, Δ)
   @. Δ *= decay
 end
 
+"""
+`WeightDecay(wd)`
+
+Decay the weight parameter by `wd`
+"""
 mutable struct WeightDecay
   wd::Real
 end