From 0766b29d1e540f8cf2c9676ef061728b1a3516db Mon Sep 17 00:00:00 2001 From: Andreas Dutzler Date: Sun, 9 Jun 2024 11:01:00 +0200 Subject: [PATCH] Update index.rst --- docs/index.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/index.rst b/docs/index.rst index b9d3e1d..c8cce70 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -9,7 +9,7 @@ Documentation .. admonition:: Highlights - Write differentiable code with Tensors based on NumPy arrays - - Designed to operate on input arrays with (elementwise-operating) trailing axes + - Efficient evaluation of batches by elementwise-operating trailing axes - Essential vector/tensor Hyper-Dual number math, including limited support for ``einsum`` (restricted to max. three operands) - Math is limited but similar to NumPy, try to use ``import tensortrax.math as tm`` instead of ``import numpy as np`` inside functions to be differentiated - Forward Mode Automatic Differentiation (AD) using Hyper-Dual Tensors, up to second order derivatives