Merge pull request #78 from pitmonticone/master

Fixed typos in the docs

Author: CarloLucibello

README.md

@@ -18,7 +18,7 @@ Among its features:
 
 ## Installation
 
-GNN.jl is a registered julia package. You can easily install it through the package manager:
+GraphNeuralNetworks.jl is a registered Julia package. You can easily install it through the package manager:
 
 ```julia
 pkg> add GraphNeuralNetworks
@@ -30,7 +30,7 @@ Usage examples can be found in the [examples](https://github.com/CarloLucibello/
 
 ## Acknowledgments
 
-GNN.jl is largely inspired by [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/), [Deep Graph Library](https://docs.dgl.ai/),
+GraphNeuralNetworks.jl is largely inspired by [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/), [Deep Graph Library](https://docs.dgl.ai/),
 and [GeometricFlux.jl](https://fluxml.ai/GeometricFlux.jl/stable/).
 
 

docs/src/datasets.md

@@ -1,4 +1,4 @@
 # Datasets
 
-GNN.jl doesn't come with its own datasets, but leverages those available in the julia (and non-julia) ecosytem. In particular, the [examples in the GNN.jl repository](https://github.com/CarloLucibello/GraphNeuralNetworks.jl/tree/master/examples) make use of the [MLDatasets.jl](https://github.com/JuliaML/MLDatasets.jl) package. There you will find common graph datasets sich as Cora, PubMed, and Citeseer.
-Also MLDatasets gives access to the [TUDataset](https://chrsmrrs.github.io/datasets/docs/datasets/) repository and its numerous datasets.
+GraphNeuralNetworks.jl doesn't come with its own datasets, but leverages those available in the Julia (and non-Julia) ecosystem. In particular, the [examples in the GraphNeuralNetworks.jl repository](https://github.com/CarloLucibello/GraphNeuralNetworks.jl/tree/master/examples) make use of the [MLDatasets.jl](https://github.com/JuliaML/MLDatasets.jl) package. There you will find common graph datasets such as Cora, PubMed, and Citeseer.
+Also MLDatasets gives access to the [TUDataset](https://chrsmrrs.github.io/datasets/docs/datasets/) repository and its numerous datasets.

docs/src/index.md

@@ -1,7 +1,7 @@
 # GraphNeuralNetworks
 
 This is the documentation page for [GraphNeuralNetworks.jl](https://github.com/CarloLucibello/GraphNeuralNetworks.jl), a graph neural network library written in Julia and based on the deep learning framework [Flux.jl](https://github.com/FluxML/Flux.jl).
-GNN.jl is largely inspired by [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/),[Deep Graph Library](https://docs.dgl.ai/),
+GraphNeuralNetworks.jl is largely inspired by [PyTorch Geometric](https://pytorch-geometric.readthedocs.io/en/latest/),[Deep Graph Library](https://docs.dgl.ai/),
 and [GeometricFlux.jl](https://fluxml.ai/GeometricFlux.jl/stable/).
 
 Among its features:
@@ -52,7 +52,7 @@ GNNGraph:
 
 ### Model building 
 
-We concisely define our model as a [`GNNChain`](@ref) containing 2 graph convolutaional 
+We concisely define our model as a [`GNNChain`](@ref) containing 2 graph convolutional 
 layers. If CUDA is available, our model will live on the gpu.
 
 ```julia
@@ -72,7 +72,7 @@ julia> opt = ADAM(1f-4);
 
 ### Training 
 
-Finally, we use a standard Flux training pipeling to fit our dataset.
+Finally, we use a standard Flux training pipeline to fit our dataset.
 Flux's DataLoader iterates over mini-batches of graphs 
 (batched together into a `GNNGraph` object). 
 

docs/src/messagepassing.md

@@ -16,7 +16,7 @@ and to ``\gamma_x`` and ``\gamma_e`` as to the node update and edge update funct
 respectively. The aggregation ``\square`` is over the neighborhood ``N(i)`` of node ``i``, 
 and it is usually equal either to ``\sum``, to `max` or to a `mean` operation. 
 
-In GNN.jl, the function [`propagate`](@ref) takes care of materializing the
+In GraphNeuralNetworks.jl, the function [`propagate`](@ref) takes care of materializing the
 node features on each edge, applying the message function, performing the
 aggregation, and returning ``\bar{\mathbf{m}}``. 
 It is then left to the user to perform further node and edge updates,
@@ -144,4 +144,4 @@ See the [`GATConv`](@ref) implementation [here](https://github.com/CarloLucibell
 ## Built-in message functions
 
 In order to exploit optimized specializations of the [`propagate`](@ref), it is recommended 
-to use built-in message functions such as [`copy_xj`](@ref) whenever possible. 
+to use built-in message functions such as [`copy_xj`](@ref) whenever possible. 

docs/src/models.md

@@ -87,7 +87,7 @@ model = GNNChain(GCNConv(din => d),
 
 The `GNNChain` only propagates the graph and the node features. More complex scenarios, e.g. when also edge features are updated, have to be handled using the explicit definition of the forward pass. 
 
-A `GNNChain` oppurtunely propagates the graph into the branches created by the `Flux.Parallel` layer:
+A `GNNChain` opportunely propagates the graph into the branches created by the `Flux.Parallel` layer:
 
 ```julia
 AddResidual(l) = Parallel(+, identity, l)  # implementing a skip/residual connection
@@ -105,7 +105,7 @@ y = model(g, X) # output size: (dout, g.num_graphs)
 ## Embedding a graph in the model
 
 Sometimes it is useful to consider a specific graph as a part of a model instead of 
-its input. GNN.jl provides the [`WithGraph`](@ref) type to deal with this scenario.
+its input. GraphNeuralNetworks.jl provides the [`WithGraph`](@ref) type to deal with this scenario.
 
 ```julia
 chain = GNNChain(GCNConv(din => d, relu),