Artificial Brain

The paper introduces an innovative approach for teaching design with logic control. The proposed approach is based on:(a) a representation of the controlled system in a form of its control and operational interacting portions;(b) atomic requirement (ATR) specifications of the system. The ATR-based approach can be supported by a formal notation of transition formulae. Each of the ATRs corresponds to its specific formula. ATRs with the algebra of transition formulae can be considered as a theoretical basis in teaching logic control. ...

This paper presents an approach to predicting the feasibility of artificial brains in the future. We focus on biomimetic neural models and electronic circuits that implement those models. Complexities in modeling biological neural tissue are discussed. Estimates are given for the size of artificial neural systems based on CMOS technology in 2021, without considering interconnections. We propose some solutions to the problem of interconnecting neurons. However, the best solution to this issue is an ongoing research topic.

This paper presents an approach to predicting the feasibility of artificial brains in the future. We focus on biomimetic neural models and electronic circuits that implement those models. Complexities in modeling biological neural tissue are discussed. Estimates are given for the size of artificial neural systems based on CMOS technology in 2021, without considering interconnections. We propose some solutions to the problem of interconnecting neurons. However, the best solution to this issue is an ongoing research topic.

This paper presents a sample of what evolved neural net circuit modules using the socalled "CoDi-1Bit" neural net model can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot "Robokoneko". It looks as though the figure is more likely to be 40 million, but the numbers are not of great concern. What is more important is the issue of evolvability of the cellular automata (CA) based neural net circuits which grow and evolve in special FPGA (Field Programmable Gate Array) hardware, at hardware speeds (e.g. updating 150 billion CA cells per second, and performing a complete run of a genetic algorithm, i.e. tens of thousands of circuit growths and fitness evaluations, to evolve the elite neural net circuit in about 1 second). The specialized hardware which performs this evolution is labeled the CAM-Brain Machine (CBM). It implements the CoDi-1Bit model, and will be delivered to ATR probably in January 1999. The CBM should make practical the assemblage of 10,000s of evolved neural net modules into humanly defined artificial brains. For the past few months, the latest hardware version of the CBM has been simulated in software to see just how evolvable and functional individual evolved modules can be. This paper reports on some of the results of these simulations. 2 The "CoDi-1Bit" Neural Network Model & CAM-Brain Machine (CBM) The CBM implements a so called "CoDi" (i.e. Collect and Distribute) [1] neural model. It is a simplified cellular automata based neural network model developed at ATR HIP

This paper reports on efforts to evolve an optimum de/convo-lution function to be used to convert analog to binary signals (spike trains) and vice versa for the binary input/output signals of the neural net circuit modules evolved at electronic speeds by the so-called "CAM-Brain Machine (CBM)" of ATR's Artificial Brain Project [1, 2, 3]. The CBM is an FPGA based piece of hardware which will be used to evolve tens of thousands of cellular automata based neural network circuits or modules at electronic speeds in about a second each, which are then downloaded into humanly architected artificial brains in a large RAM space [2, 3]. Since state-of-the-art programmable FPGAs constrained us to use 1 bit binary signaling in our neural model (the "CoDi-1Bit" model [4]), an efficient de/convolution technique is needed to convert digital signals to analog and vice versa, so that "evolutionary engineers" (EEs) who evolve the many modules, can think it terms of ...

This paper presents some simulation results of the evolution of 2D visual pattern recognizers to be implemented very shortly on real hardware, namely the \CAM-Brain Machine" (CBM), an FPGA based piece of evolvable hardware which implements a genetic algorithm (GA) to evolve a 3D cellular automata (CA) based neural network circuit module, of approximately 1,000 neurons, in about a second, i.e. a complete run of a GA, with 10,000s of circuit growths and performance evaluations. Up to 65,000 of these modules, each of which is evolved with a humanly speci ed function, can be downloaded into a large RAM space, and interconnected according to humanly speci ed arti cial brain architectures. This RAM, containing an arti cial brain with up to 75 million neurons, is then updated by the CBM at a rate of 130 billion CA cells per second. Such speeds will enable real time control of robots and hopefully the birth of a new research eld that we call \brain building". The rst such arti cial brain, to be built at STARLAB in 2000 and beyond, will be used to control the behaviors of a life sized kitten robot called \Robokitty". This kitten robot will need 2D pattern recognizers in the visual section of its arti cial brain. This paper presents simulation results on the evolvability and generalization properties of such recognizers.

A major challenge in performing pattern recognition with neural networks is large input data sets; for example, high-resolution static images. There is a direct relationship between the number of inputs and the number of neurons and links required to process those inputs. Specifically, as the number of inputs increases linearly, the complexity of the neural net increases exponentially. We present a new approach to pattern recognition, where input data is “streamed” into a feedback neural net. This is done by distributing the input temporally, such that a portion of the inputs is used for each iteration of the neural net. Therefore, pattern recognition is automatically performed in conveniently sized segments with a single neural net. This reduces the amount of evolution that must be performed to train the neural net.

This paper reports on e orts to evolve an optimum de/convolution function to be used to convert analog to binary signals (spike trains) and vice versa for the binary input/output signals of the neural net circuit modules evolved at electronic speeds by the so-called "CAM-Brain Machine (CBM)" of ATR's Arti cial Brain Project 1, 2, 3]. The CBM is an FPGA based piece of hardware which will be used to evolve tens of thousands of cellular automata based neural network circuits or modules at electronic speeds in about a second each, which are then downloaded into humanly architected arti cial brains in a large RAM space 2, 3]. Since state-of-the-art programmable FPGAs constrained us to use 1 bit binary signaling in our neural model (the "CoDi-1Bit" model 4]), an e cient de/convolution technique is needed to convert digital signals to analog and vice versa, so that "evolutionary engineers" (EEs) who evolve the many modules, can think it terms of analog signals when they need to, rather than in terms of the abstract incomprehensible spike trains (where the information in the signal is contained in the spacing between spikes). An earlier convolution function, digitized from a text book gure 7] (shown in Fig. 1), gave only moderate accuracy between actual and desired output results. By applying a genetic algorithm to the evolution of the de/convolution function we were able to make it nearly twice as accurate. Accuracy is important so as to reduce cumulative errors when the output of one neural net module becomes the input of another, in long sequential chains of modules in arti cial brain architectures consisting of 10,000s of modules. The CBM can handle up to 32000 modules (of maximum about 1000 arti cial neurons each) and will be delivered to ATR by the spring of 1999.

The "China Brain Project" is a 4 year (2008-2011), 10.5 million RMB research project to build China's first artificial brain, which will consist of 10,000-50,000 neural net modules which are evolved rapidly in special FPGA hardware, downloaded one by one into a PC or supercomputer, and then connected according to the designs of human "BAs" (brain architects) to build an artificial brain with thousands of pattern detectors to control the hundreds of behaviors of a two legged robot.

This position paper discusses the evolution of multi-module neural net systems, where the number of neural net modules is up to ten million (i.e. an "artificial brain"). ATR's "CAM-Brain" Project [de Garis 1993, 1996] has progressed to the point where it is technically possible (using a new FPGA (Field Programmable Gate Array) based evolvable hardware (EHW or E-Hard) system to be completed by the spring of 1998 [Korkin & de Garis 1997]) to begin to evolve and build an artificial brain containing 10,000 neural net modules. This development raises the prospect that within a few years these numbers will rapidly increase. This paper introduces some issues that such massive systembuilding will generate. The immediate question is "What should we evolve?" This paper presents some suggested evolvable system targets containing N neural net modules, where N =

This paper describes ongoing ATR's CAM-Brain Project, which is an attempt to build large-scale neural networks ('artificial brains') in a special hardware called "CAM-Brain Machine" (CBM). At the time of writing (March 1998), the project is making efforts on two fronts - the construction of the CBM, that is scheduled to be operational in the summer of 1998, and attempting to find an efficient and effective representation for the binary signaling of ATR's CAM-Brain Machine (CBM), using the so-called "CoDi-1Bit" model. The CBM is an FPGA based hardware accelerator which updates 3D cellular automata (CA) cells at the rate of 100 billion a second, allowing a complete run of a genetic algorithm with tens of thousands of CA based neural net circuit growths and hardware compiled fitness evaluations. It is hoped that 1 In the Proceedings of the 1998 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA'98),...

We propose a Universal Spiketrain Processor (USP)-a computing device for high-speed execution of Pulsed Para-Neural Networks (PPNN). PPNN is a graph consisting of processing nodes and directed edges, called axons. We provide a description of USP architecture, a USP-specific language of PPNN coding, and methods of conversion of the already existing PPNN code into a USP code. We also compare the USP's performance with the already existing cellular-automata-based tools for PPNN simulation.

Prof. Hugo de Garis has recently received a 3 million RMB, 4 year grant to build China's first artificial brain, starting in 2008, that will consist of approximately 15,000 interconnected neural net modules, evolved one at a time in a special accelerator board [1] (which is 50 times faster than using an ordinary PC) to control the hundreds of behaviors of an autonomous robot. The approach taken in building this artificial brain is fast and cheap (e.g. $1500 for the FPGA board, $1000 for the robot, and $500 for the PC, a total of $3000), so we hope that other brain building groups around the world will copy this evolutionary engineering approach.

This paper presents a sample of what evolved neural net circuit modules using the socalled "CoDi-1Bit" neural net model can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot "Robokoneko". It looks as though the figure is more likely to be 40 million, but the numbers are not of great concern. What is more important is the issue of evolvability of the cellular automata (CA) based neural net circuits which grow and evolve in special FPGA (Field Programmable Gate Array) hardware, at hardware speeds (e.g. updating 150 billion CA cells per second, and performing a complete run of a genetic algorithm, i.e. tens of thousands of circuit growths and fitness evaluations, to evolve the elite neural net circuit in about 1 second). The specialized hardware which performs this evolution is labeled the CAM-Brain Machine (CBM). It implements the CoDi-1Bit model, and will be delivered to ATR probably in January 1999. The CBM should make practical the assemblage of 10,000s of evolved neural net modules into humanly defined artificial brains. For the past few months, the latest hardware version of the CBM has been simulated in software to see just how evolvable and functional individual evolved modules can be. This paper reports on some of the results of these simulations.

This article introduces the “CAM-Brain Machine” (CBM), an FPGA based piece of hardware which implements a genetic algorithm (GA) to evolve a cellular automata (CA) based neural network circuit module, of approximately 1,000 neurons, in about a second, i.e., a complete run of a GA, with 10,000s of circuit growths and performance evaluations. Up to 65,000 of these modules, each of which is evolved with a humanly specified function, can be downloaded into a large RAM space, and interconnected according to humanly specified artificial brain architectures. This RAM, containing an artificial brain with up to 75 million neurons, is then updated by the CBM at a rate of 130 billion CA cells per second. Such speeds should enable real time control of robots and hopefully the birth of a new research field that we call “brain building.” The first such artificial brain, to be built in 2000 and beyond, will be used to control the behaviors of a life sized robotkitten called “Robokitty.”

Our  goal is to create a fully brain simulation software, what will have ability to recognize “friend or foe”, to learn languages, to “think” about the ways of solving problems, always having selections to choose optimal solutions, even to joke, feel boring etc.

This work presents a sample of what evolved neural net circuit modules using the socalled “CoDi-1 Bit” neural net model can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot “Robokoneko”. It looks as though the figure is more likely to be 40 million, but the numbers are not of great concern. What is more important is the issue of evolvability of the cellular automata (CA) based neural net circuits which grow and evolve in special FPGA (Field Programmable Gate Array) hardware, at hardware speeds (e.g. updating 150 billion CA cells per second, and performing a complete run of a genetic algorithm, i.e. tens of thousands of circuit growths and fitness evaluations to evolve the elite neural net circuit in about 1 second). The specialized hardware which performs this evolution is labeled the CAM-Brain Machine (CBM). It implements the CoDi-1 Bit model, and was delivered to ATR in May 1999. The CBM should make practical the assemblage of 10,000s of evolved neural net modules into humanly defined artificial brain architectures. For the past few months, the latest hardware version of the CBM has been simulated in software to see just how evolvable and functional individual evolved modules can be. This work reports on some of the results of these simulations, for which the input/output is either binary or analog

The paper presents a sample of what evolved neural net circuit modules using the so called “CoDi-1Bit” neural net model can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot “Robokoneko”. It looks as though the figure is more likely to be 40 million, but the numbers are not of great concern. What is more important is the issue of evolvability of the cellular automata (CA) based neural net circuits which grow and evolve in special FPGA (field programmable gate array) hardware, at hardware speeds, e.g. updating 150 billion CA cells per second, and performing a complete run of a genetic algorithm, i.e. tens of thousands of circuit growths and fitness evaluations, to evolve the elite neural net circuit in about 1 second. The specialized hardware which performs this evolution is labeled the CAM-Brain Machine (CBM). It implements the CoDi-1Bit model, and will be delivered to ATR probably in January 1999. The CBM should make practical the assemblage of 10000s of evolved neural net modules into humanly defined artificial brains. For the past few months, the latest hardware version of the CBM has been simulated in software to see just how evolvable and functional individual evolved modules can be. The paper reports on some of the results of these simulations

This paper introduces a Partially Connected Neural Evolutionary (Parcone) model and its application to object and gesture recognition as part of the "China Brain Project", which aims to build China's first artificial brain, consisting of 10,000s of evolved interconnected neural net modules, each with its own little task, similar to Minsky's agents.