sudo apt install build-essential opencl-dev

./bisuna resources/FPGAConf.ini  # Run Binary Neurons
./suna resources/FPGAConf.ini # Run Continuous Neurons

@inproceedings{8953134,
	Abstract = {With the explosive interest in the utilization of Neural Networks, several approaches have taken place to make them faster, more accurate or power efficient; one technique used to simplify inference models is the utilization of binary representations for weights, activations, inputs and outputs. This paper presents a novel approach to train from scratch Binary Neural Networks using neuroevolution as its base technique (gradient descent free), to then apply such results to standard Reinforcement Learning environments tested in the OpenAI Gym. The results and code can be found in https://github.com/rval735/BiSUNA.},
	Author = {R. {Valencia} and C. {Sham} and O. {Sinnen}},
	Booktitle = {2019 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)},
	Date-Added = {2020-01-20 16:32:29 +1300},
	Date-Modified = {2020-01-20 16:32:40 +1300},
	Doi = {10.1109/APCCAS47518.2019.8953134},
	Issn = {null},
	Keywords = {BNN; Neuroevolution;binary neural networks;BiSUNA;discrete optimization},
	Month = {Nov},
	Pages = {301-304},
	Title = {Using Neuroevolved Binary Neural Networks to solve reinforcement learning environments},
	Year = {2019},
	Bdsk-Url-1 = {https://doi.org/10.1109/APCCAS47518.2019.8953134}}

@inproceedings{8977877,
	Abstract = {The exponential progress of semiconductor tech-nologies has enabled the proliferation of deep learning as a prominent area of research, where neural networks have demon-strated its effectiveness to solve very hard multi dimensional problems. This paper focuses on one in particular, Binary Neural Networks (BNN), which use fixed length bits in its connections and logic functions to perform excitation operations. Exploiting those characteristics, hardware accelerators that integrate field-programmable gate arrays (FPGAs) have been adopted to hasten inference of deep learning networks, given its proficiency to maximize parallelism and energy efficiency. This work will show how the algorithm Binary Spectrum-diverse Unified Neuroevolution Architecture (BiSUNA) can perform training and inference on FPGA without the need of gradient descent. Source code can be found in github.com/rval735/bisunaocl},
	Author = {R. {Valencia} and C. W. {Sham} and O. {Sinnen}},
	Booktitle = {2019 International Conference on Field-Programmable Technology (ICFPT)},
	Date-Added = {2020-02-04 20:40:00 +1300},
	Date-Modified = {2020-02-04 20:40:39 +1300},
	Doi = {10.1109/ICFPT47387.2019.00076},
	Issn = {null},
	Keywords = {BNN, FPGA;BiSUNA;Binary Neural Network;TWEANN;Evolutionary Algorithm},
	Month = {Dec},
	Pages = {395-398},
	Title = {Evolved Binary Neural Networks Through Harnessing FPGA Capabilities},
	Year = {2019},
	Bdsk-Url-1 = {https://doi.org/10.1109/ICFPT47387.2019.00076}}

@inproceedings{10.1145/3377929.3389933,
	author = {R. {Valencia}, and Sham, Chiu Wing and Vargas, Danilo Vasconcellos},
	title = {Preliminary Study of Applied Binary Neural Networks for Neural Cryptography},
	year = {2020},
	isbn = {9781450371278},
	publisher = {Association for Computing Machinery},
	address = {New York, NY, USA},
	url = {https://doi.org/10.1145/3377929.3389933},
	doi = {10.1145/3377929.3389933},
	booktitle = {Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion},
	pages = {291–292},
	numpages = {2},
	keywords = {CPA, binary neural network, BiSUNA, adversarial neurocryptography, neuroevolution},
	location = {Canc\'{u}n, Mexico},
	series = {GECCO ’20}
	}