Deep learning in neural networks: An overview

J Schmidhuber - Neural networks, 2015 - Elsevier
In recent years, deep artificial neural networks (including recurrent ones) have won
numerous contests in pattern recognition and machine learning. This historical survey …

BSA, a fast and accurate spike train encoding scheme

B Schrauwen… - Proceedings of the …, 2003 - ieeexplore.ieee.org
In this paper we introduce a new algorithm for encoding analog information into spike trains,
given that the reconstruction will take place using a FIR filter. An older technique called HSA …

The CAM-Brain Machine (CBM): an FPGA-based hardware tool that evolves a 1000 neuron-net circuit module in seconds and updates a 75 million neuron artificial …

H De Garis, M Korkin - Neurocomputing, 2002 - Elsevier
This article introduces the “CAM-Brain Machine”(CBM), an FPGA-based piece of hardware
that implements a genetic algorithm (GA) to evolve a cellular automata (CA)-based neural …

CoDi-1Bit: A simplified cellular automata based neuron model

F Gers, H De Garis, M Korkin - … : Third European Conference AE'97 Nîmes …, 1998 - Springer
This paper presents some simplifications to our recently introduced “CoDi-model”, which we
use to evolve Cellular Automata based neural network modules for ATR's artificial brain …

HereBoy: A fast evolutionary algorithm

D Levi - Proceedings. The Second NASA/DoD Workshop on …, 2000 - ieeexplore.ieee.org
HereBoy is an evolutionary algorithm that combines features from genetic algorithms and
simulated annealing, and also adds a new methodology for exploring the search space. It is …

GeneticFPGA: Evolving stable circuits on mainstream FPGA devices

D Levi, SA Guccione - Proceedings of the first NASA/DOD …, 1999 - ieeexplore.ieee.org
GeneticFPGA is a Java-based tool for evolving digital circuits on Xilinx XC4000EX/sup
TM/and XC4000XL/sup TM/devices. Unlike other FPGA architectures popular with …

[PDF][PDF] SPIKER: Analog waveform to digital spiketrain conversion in ATR's artificial brain (cam-brain) project

M Hough, H De Garis, M Korkin, F Gers… - … conference on robotics …, 1999 - researchgate.net
This paper presents an algorithm which converts an arbitrary analog time-varying signal into
a digital spiketrain (a bit string of 0's interspersed with 1's), where the information is …

Long short-term memory learns context free and context sensitive languages

FA Gers, J Schmidhuber - Artificial Neural Nets and Genetic Algorithms …, 2001 - Springer
Previous work on learning regular languages from exemplary training sequences showed
that Long Short-Term Memory (LSTM) outperforms traditional recurrent neural networks …

Building an artificial brain using an FPGA based CAM-Brain Machine

H De Garis, M Korkin, F Gers, E Nawa… - Applied Mathematics and …, 2000 - Elsevier
Building an artificial brain using an FPGA based CAM-Brain Machine - ScienceDirect Skip
to main contentSkip to article Elsevier logo Journals & Books Search RegisterSign in View …

A “spike interval information coding” representation for ATR's CAM-Brain machine (CBM)

M Korkin, NE Nawa, H De Garis - International Conference on Evolvable …, 1998 - Springer
This paper reports on ongoing attempts to find an efficient and effective representation for
the binary signaling of ATR's CAM-Brain Machine (CBM), using the so-called” CoDi-1Bit” …