Update README.md

README.md

@@ -5,7 +5,7 @@
 
 <p align="center"><img src="https://github.com/braindynamicslab/neumapper/blob/master/docs/assets/neumapper_pipeline.png" width="75%"></p>
 
-Developed with neuroimaging data analysis in mind, NeuMapper implements a novel landmark-based intrinsic binning strategy that eliminates the need for dimensionality reduction. Rather than projecting the high-dimensional data to a low-dimensional embedding, NeuMapper stays in high-dimensional space and performs the binning directly on a reciprocal kNN graph. By using geodesic distances, NeuMapper is able to better captures the high-dimensional, non-linear structure underlying the dynamical landscape of brain activity.
+Developed with neuroimaging data analysis in mind, NeuMapper implements a novel landmark-based intrinsic binning strategy that eliminates the need for dimensionality reduction. Rather than projecting the high-dimensional data to a low-dimensional embedding, NeuMapper stays in high-dimensional space and performs the binning directly on a reciprocal kNN graph. By using geodesic distances, NeuMapper is able to better capture the high-dimensional, non-linear structure underlying the dynamical landscape of brain activity.
 
 NeuMapper was designed specifically for working with complex, high-dimensional neuroimaging data and produces a shape graph representation that can be annotated with meta-information and further examined using network science tools. These shape graphs can be visualized using [DyNeuSR](https://braindynamicslab.github.io/dyneusr/), a Python visualization library that provides a custom web interface for exploring and interacting with shape graphs, and several other tools for anchoring these representations back to neurophysiology and behavior. To see how NeuMapper and DyNeuSR can be used together to create beautiful visualizations of high-dimensional data, check out the [examples](https://github.com/braindynamicslab/neumapper/tree/master/examples/) folder.