From 881bf859ebd506cff9a9e9e4cd87d5a1a4767ab1 Mon Sep 17 00:00:00 2001 From: Alex Morehead Date: Wed, 1 May 2024 21:44:30 -0500 Subject: [PATCH] Fix small typo in `README.md` --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 8cc13a2..4636e7e 100644 --- a/README.md +++ b/README.md @@ -53,7 +53,7 @@ Check our [docs](https://torchdyn.readthedocs.io/) for more information. Interest in the blend of differential equations, deep learning and dynamical systems has been reignited by recent works [[1](https://arxiv.org/abs/1806.07366),[2](https://arxiv.org/abs/2001.04385), [3](https://arxiv.org/abs/2002.08071), [4](https://arxiv.org/abs/1909.01377)]. Modern deep learning frameworks such as PyTorch, coupled with further improvements in computational resources have allowed the continuous version of neural networks, with proposals dating back to the 80s [[5](https://ieeexplore.ieee.org/abstract/document/6814892)], to finally come to life and provide a novel perspective on classical machine learning problems. -We explore how differentiable programming can unlock the effectiveness of deep learning to accelerate progress across scientific domains, including control, fluid dynamics and in general prediction of complex dynamical systems. Conversely, we focus on models powered by numerical methods and signal processing to advance the state of AI in classical domains such as vision of natural language. +We explore how differentiable programming can unlock the effectiveness of deep learning to accelerate progress across scientific domains, including control, fluid dynamics and in general prediction of complex dynamical systems. Conversely, we focus on models powered by numerical methods and signal processing to advance the state of AI in classical domains such as vision or natural language.