N2S3 1.0 is mainly an infrastructure release oriented towards the ease of development and distribution. Besides, there were are also some news in the core of the simulator and the documentation. Here you have the major changes:
Infrastructure:
- N2S3 is now an SBT multi-project [1]
- Better integration with IntelliJ IDEA and Eclipse [2]
- Supporting the system's distribution:
- Clustering support
- Refactoring to support the dynamic deployment of actors in different cluster nodes.
- Two deployment strategies were implemented so far: Random and concrete actor.
- Fixes in the core to make it distributable. E.g, fixed serialization of messages, global state.
- The Continuous Integration service was extended and enhanced [4]
- A new input mechanism was implemented [5, 6]
Core:
- Added bio-inspired model i.e., a model with parameters similar to those in the nature.
- Added supervised learning algorithm SpikeProp
- Examples of Mnist/Freeway/sevenSegment with the bio-inspired model.
- Example of Masquelier's experiment: Spike Timing Dependent Plasticity Finds the Start of Repeating Patterns in Continuous Spike Trains
- Added Supervised Xor, an example of learning the Xor function with SpikeProp (Error-backpropagation in temporally encoded networks of spiking neurons)
- Preliminar version of an example of direction detection with reservoir computing (using supervised STDP and only 2 directions)
Documentation:
- The core scaladocs were entirely revisited
- Technical documentation about the core implementation can be found in [7]
