Update README.md

README.md

@@ -12,17 +12,20 @@ metrics:
 - accuracy
 ---
 
-### Description of the ImageNet-1k Featured Model
-For a thorough description of our models trained on the ImageNet-1k dataset, please read our preprint, 
-*Towards Errorless Training ImageNet-1k*, which is available at [ADD LINK to arXiv preprint]. 
-In ../ImageNet-1k/MATLAB, we give parameters for 6 models, which are listed in the table below. 
-Each model has the following architecture: 17x40x2=1360 FNNs, all with homogeneous architecture (900-256-25 or 900-256-77-25), 
-working in parrallel to produce 1360 predictions which determine a final prediction using the majority voting protocol. 
-We trained models using the following transformation of the 64x64 downsampled ImageNet-1k dataset:
+# Towards Errorless Training ImageNet-1k
+This repository host code and models for the manuscript, *Towards Errorless Training ImageNet-1k*, which is available at [ADD LINK to arXiv preprint].
+We give 6 models trained on the ImageNet-1k dataset, which we list in the table below.
+Each model is featured model of archtecture 17x40x2. 
+That is, each model is made up of 17x40x2=1360 FNNs, all with homogeneous architecture (900-256-25 or 900-256-77-25), 
+working in parallel to produce 1360 predictions which determine a final prediction using the majority voting protocol.
+
+We trained the 6 models using the following transformation of the 64x64 downsampled ImageNet-1k dataset:
  - downsampled images to 32x32, using the mean values of non-overlapping 2x2 grid cells and
  - trimmed off top row, bottom row, left-most column, and right-most column.
 
- This transformed data results in 30x30 images, hence 900-dimensional input vectors.
+This transformed data results in 30x30 images, hence 900-dimensional input vectors.
+
+For a thorough description of our models trained on the ImageNet-1k dataset, please read our preprint linked above.
 
 
 | Model | Training Method | FNN Architecture | Accuracy (%) |