Hardware-Oriented models for VLSI implementation of Self-Organizing Maps

Martin-del-Brio, B.; Blasco-Alberto, Javier

doi:10.1007/3-540-59497-3_242

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This formulation of the output layer activation has some advantages (Martín-del Brío and Blasco-Alberto, 1995 ), so we use it here. In particular, it is biologically plausible and allows the comparison of the units activations with a threshold (see below in this section).…”

Section: Methodsmentioning

confidence: 99%

Know Your Body Through Intrinsic Goals

et al. 2018

View full text Add to dashboard Cite

The first “object” that newborn children play with is their own body. This activity allows them to autonomously form a sensorimotor map of their own body and a repertoire of actions supporting future cognitive and motor development. Here we propose the theoretical hypothesis, operationalized as a computational model, that this acquisition of body knowledge is not guided by random motor-babbling, but rather by autonomously generated goals formed on the basis of intrinsic motivations. Motor exploration leads the agent to discover and form representations of the possible sensory events it can cause with its own actions. When the agent realizes the possibility of improving the competence to re-activate those representations, it is intrinsically motivated to select and pursue them as goals. The model is based on four components: (1) a self-organizing neural network, modulated by competence-based intrinsic motivations, that acquires abstract representations of experienced sensory (touch) changes; (2) a selector that selects the goal to pursue, and the motor resources to train to pursue it, on the basis of competence improvement; (3) an echo-state neural network that controls and learns, through goal-accomplishment and competence, the agent's motor skills; (4) a predictor of the accomplishment of the selected goals generating the competence-based intrinsic motivation signals. The model is tested as the controller of a simulated simple planar robot composed of a torso and two kinematic 3-DoF 2D arms. The robot explores its body covered by touch sensors by moving its arms. The results, which might be used to guide future empirical experiments, show how the system converges to goals and motor skills allowing it to touch the different parts of own body and how the morphology of the body affects the formed goals. The convergence is strongly dependent on competence-based intrinsic motivations affecting not only skill learning and the selection of formed goals, but also the formation of the goal representations themselves.

show abstract

Section: Methodsmentioning

confidence: 99%

Know Your Body Through Intrinsic Goals

et al. 2018

View full text Add to dashboard Cite

show abstract

“…As is suggested in [3,41, this peculiarity should be exploited in order to attaining faster speed devices or integrating more neurons. In this sense, in a previous work [4] we have introduced and broadly tested by computer simulations a simple 'digital SOFM' . This simplified model implements minimal expressions from the digital VLSI point of view for different features of the SOFM model:…”

Section: A Simplified Sofm Modelmentioning

confidence: 98%

“…Precision bits: we find that 8 bit integers (for inputs and synaptic weights) are enough for several typical problems studied [4].…”

Section: A Simplified Sofm Modelmentioning

confidence: 99%

“…Distance measure: Manhattan distance is simpler than the conventional Euclidean one Weight updating: We derive the following learning rule from the Manhattan distance [3,4] A w g k ( t ) = a ( t ) , s i~~x k ( t j -w , k ( f ) ) (2) Thus, the learning process only consists of adding or subtracting the learning rate a@.…”

Section: A Simplified Sofm Modelmentioning

confidence: 99%

“…In Sect. I1 a hardware-oriented model for the SOFM, that we E-mail: niki@zape.unizar.es introduced in a previous work [4], is reviewed. In Sect.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A low-cost neuroprocessor board for emulating the SOFM neural model

Martin-del-Brio

Marques²,

Hernández-Sánchez³

1998 IEEE International Conference on Electronics, Circuits and Systems. Surfing the Waves of Science and Technology (Cat. No.9

View full text Add to dashboard Cite

In this paper, the design and implementation of a low-cost PC-board for emulating the self-organising map neural model is shown. This neuroprocessor, based on Xilinx's FPGAs, is built and tested, and its performance is analysed and compared to computer simulations. The resulting neuroboard is just a first step towards the development of a general purpose neuroemulator based on FPGAs, in which the reconfiguration properties of these programmable logic devices will be broadly exploited.

show abstract

Biologically-inspired digital circuit for a self-organising neural network

Pérez

Luque²,

Damiani³

Proceedings of the 1998 Second IEEE International Caracas Conference on Devices, Circuits and Systems. ICCDCS 98. On the 70th A

View full text Add to dashboard Cite

Hardware-Oriented models for VLSI implementation of Self-Organizing Maps

Cited by 5 publications

References 8 publications

Know Your Body Through Intrinsic Goals

Know Your Body Through Intrinsic Goals

A low-cost neuroprocessor board for emulating the SOFM neural model

Biologically-inspired digital circuit for a self-organising neural network

Contact Info

Product

Resources

About