@@ -10,8 +10,8 @@ Five is right out.
11💣 Machine learning which might blow up in your face 💣
11💣 Machine learning which might blow up in your face 💣
13−Grenade is a dependently typed, practical, and fast neural network library for
13+Grenade is a dependently typed, practical, and fast recurrent neural network library
14−concise and precise specifications of complex networks in Haskell.
14+for concise and precise specifications of complex networks in Haskell.
16As an example, a network which can achieve ~1.5% error on MNIST can be
16As an example, a network which can achieve ~1.5% error on MNIST can be
17specified and initialised with random weights in a few lines of code with
17specified and initialised with random weights in a few lines of code with