Updated Release Notes for v0.102.

Author: bvanessen

ReleaseNotes.txt

@@ -1,4 +1,29 @@
 ============================== (Pending) Release Notes: v1.00 ==============================
+Support for new training algorithms:
+
+Support for new network structures:
+
+Support for new layers:
+
+Python front-end:
+
+Performance optimizations:
+
+Model portability & usability:
+
+Experiments & Applications:
+
+Internal features:
+
+I/O & data readers:
+
+Build system:
+
+Bug fixes:
+
+Retired features:
+
+============================== Release Notes: v0.102 ==============================
 Support for new training algorithms:
  - LTFB is now a first-class training algorithm.
  - LTFB now allows multiple metrics. The local algorithm is favored by
@@ -39,8 +64,6 @@ Performance optimizations:
  - Parallelize computation of Gaussian random numbers
  - Optimizing tessellate, concatenate, and slice layers on CPU
 
-Model portability & usability:
-
 Experiments & Applications:
  - Added experiment scripts for ATOM cWAE Gordon Bell simulations
  - LBANN-ATOM model inference and analysis