From 16573158d85cfeb7a9e95bd217640d0e8e527024 Mon Sep 17 00:00:00 2001
From: Huw Campbell <huw.campbell@ambiata.com>
Date: Thu, 19 Jan 2017 23:08:01 +1100
Subject: [PATCH] Nicer type

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 328cf0f..5685d6f 100644
--- a/README.md
+++ b/README.md
@@ -66,8 +66,8 @@ Usage
 
 To perform back propagation, one can call the eponymous function
 ```haskell
-backPropagate :: forall input target shapes layers. (Head shapes ~ input, Last shapes ~ target)
-              => Network layers shapes -> S input -> S target -> Gradients layers
+backPropagate :: forall shapes layers.
+                 Network layers shapes -> S (Head shapes) -> S (Last shapes) -> Gradients layers
 ```
 which takes a network, appropriate input and target data, and returns the
 back propagated gradients for the network. The shapes of the gradients are