GesturePod reorg (#200)

* GesturePod reorg


* Update README.md

README.md

@@ -52,9 +52,10 @@ the ICML '17 publications on [Bonsai](/docs/publications/Bonsai.pdf) and
 the NeurIPS '18 publications on [EMI-RNN](/docs/publications/emi-rnn-nips18.pdf) and
 [FastGRNN](/docs/publications/FastGRNN.pdf),
 the PLDI '19 publication on [SeeDot compiler](/docs/publications/SeeDot.pdf),
-the UIST '19 publication on [Gesturepod](/docs/publications/ICane-UIST19.pdf), 
+the UIST '19 publication on [Gesturepod](/docs/publications/GesturePod-UIST19.pdf), 
 the BuildSys '19 publication on [MSC-RNN](/docs/publications/MSCRNN.pdf),
-and the NeurIPS '19 publication on [Shallow RNNs](/docs/publications/Sha-RNN.pdf).
+the NeurIPS '19 publication on [Shallow RNNs](/docs/publications/Sha-RNN.pdf),
+and the ICML '20 publication on [DROCC](/docs/publications/drocc.pdf).
 
 
 Also checkout the [ELL](https://github.com/Microsoft/ELL) project which can

applications/GesturePod/README.md

@@ -19,4 +19,4 @@ To learn more about GesturePod, refer our [UIST'19 publication](https://github.c
 
 The benchmark dataset for Gesture recognition can be downloaded [here](https://www.microsoft.com/en-us/research/uploads/prod/2018/05/dataTR_v1.tar.gz) [MIT Open source license].
 
-_If you are using the dataset please [cite](https://dl.acm.org/downformats.cfm?id=3347881&parent_id=3332165&expformat=bibtex) GesturePod._
+_If you are using the dataset please [cite](https://dl.acm.org/doi/10.1145/3332165.3347881) GesturePod._

applications/GesturePod/onComputer/README.md

@@ -28,7 +28,7 @@ used as a basis for porting GesturePod to other  platforms.
 2. Clone the repo and navigate to this directory
 	```
 	git clone https://github.com/microsoft/EdgeML.git
-	cd EdgeML/Applications/GesturePod/onComputer
+	cd EdgeML/applications/GesturePod/onComputer
 	```
 3. Compile and build the code
 	```

applications/GesturePod/onMKR1000/README.md

@@ -19,7 +19,7 @@ GesturePod *(on MKR1000)*
 1. Clone the repo and navigate to this folder
 	```
 	git clone https://github.com/microsoft/EdgeML.git
-	cd Applications/GesturePod/onMKR1000
+	cd EdgeML/applications/GesturePod/onMKR1000
 	```
 2. Refer to this [tutorial](https://microsoft.github.io/EdgeML/Projects/GesturePod/instructable.html) to build the Hardware and setup external dependencies - [Cortex M0+ Board support](https://www.hackster.io/charifmahmoudi/arduino-mkr1000-getting-started-08bb4a).
 		

applications/GesturePod/training/README.md

@@ -29,7 +29,7 @@ Accelorometer and gyroscope values from the MPU6050 sensor is collected.
 Connect the GesturePod to computer over Serial COM Port.
 
 1. Refer
-   [here](https://github.com/microsoft/EdgeML/blob/master/Applications/GesturePod/onMKR1000/README.md#quick-start)
+   [here](https://github.com/microsoft/EdgeML/blob/master/applications/GesturePod/onMKR1000/README.md#quick-start)
 to set up the required dependencies for the MKR1000 platform.
 		
 2. Compile, Build and Upload
@@ -87,9 +87,9 @@ This will generate a `train.csv` and `test.csv` files that should be used to gen
 Using the TensorFlow / PyTorch / cpp implementation of the ProtoNN algorithm from the EdgeML repository, train a
 model on the ```train.csv``` file generated above.  Extract W, B, Z, and gamma
 values from the trained ProtoNN model. Update these values in
-```EdgeML/Applications/GesturePod/onMKR1000/src/data.h``` to deploy the model on
+```EdgeML/applications/GesturePod/onMKR1000/src/data.h``` to deploy the model on
 the GesturePod. Alternately, update
-```EdgeML/Applications/GesturePod/onComputer/src/data.h``` to simulate inference
+```EdgeML/applications/GesturePod/onComputer/src/data.h``` to simulate inference
 of the new model on your computer.
 
 Alternatively, to generate a `data.h`, you could: 

pytorch/README.md

@@ -28,7 +28,8 @@ for these algorithms are in `edgeml_pytorch.trainer`.
 4. [S-RNN](https://github.com/microsoft/EdgeML/blob/master/docs/publications/SRNN.pdf): `edgeml_pytorch.graph.rnn.SRNN2` implements a 
     2 layer SRNN network which can be instantied with a choice of RNN cell. The training
     routine for SRNN is in `edgeml_pytorch.trainer.srnnTrainer`.
-5. DROCC & DROCC-LF: `edgeml_pytorch.trainer.drocc_trainer` implements a DROCC meta-trainer for training any given model architecture
+5. [DROCC & DROCC-LF](https://github.com/microsoft/EdgeML/blob/master/docs/publications/drocc.pdf): `edgeml_pytorch.trainer.drocc_trainer` implements 
+    a DROCC meta-trainer for training any given model architecture
     for one-class classification on the supplied dataset. `edgeml_pytorch.trainer.drocclf_trainer` implements the DROCC-LF varaint
     for training models for one-class classification with limited negatives.