| 000 | 02573nam a22002897a 4500 | ||
|---|---|---|---|
| 003 | MX-MeUAM | ||
| 005 | 20250311055949.0 | ||
| 008 | 250310s2025 mx fo||d| 00| 0 spa d | ||
| 040 |
_aMX-MeUAM _bspa _cMX-MeUAM |
||
| 050 | 4 |
_aQA76.87 _bG37 2025 |
|
| 100 | 1 |
_aGarcía Campos, Carlos Alan _924790 |
|
| 245 | 1 | 2 |
_aA comparative analysis of Gabor filters and biologically inspired learning rules for image classification implementing Spiking Neural Networks _h[recurso electrónico] / _cCarlos Alan García Campos ; director, Ricardo Morales Carbajal ; codirector, Hirotsugu Okuno |
| 260 |
_aMexicali, Baja California, _c2025 |
||
| 300 |
_a1 recurso en línea, 69 p. ; _bil. col., gráficas |
||
| 500 | _aMaestría y Doctorado en Ciencias e Ingeniería | ||
| 502 | _aTesis (Maestría) - - Universidad Autónoma de Baja California, Instituto de Ingeniería, Mexicali, 2025 | ||
| 504 | _aIncluye referencias bibliográficas. | ||
| 520 | _aPlastic changes on the synapse drive by spike-timing have been of great interest as the main learning rule for spiking neural networks. Spike-timing-based rules are built to model the behavior of a region on the brain related to experimental data in neuroscience, therefore can lead to differences in the moment of implementing the rule within a spiking network. This work compares the performance of a pair-wise and a triplet STDP with different spike interactions to clear an MNIST classification task. A bio-inspired preprocessing stage was implemented that consisted of a Gabor filter (as a model of the simple cells mechanism orientation selectivity) and an input normalization for a homogeneous brightness level of each image. The highlights of this work are 1) The consistent improvement of the model accuracy whenever they added the Gabor filter to the inputs; 2) The input normalization to prevent the overfitting of the model; 3) The Gabor filter helps to correct decoding of some images of the dataset on the evaluation test. | ||
| 650 | 4 |
_aRedes neuronales (Informática) _vTesis y disertaciones académicas. |
|
| 650 | 7 |
_aRedes neurales (computadores) _vTesis y disertaciones académicas. _2lemb |
|
| 650 | 4 |
_aRedes neuronales (Informática) _xSoftware _vTesis y disertaciones académicas. |
|
| 700 | 1 |
_aMorales Carbajal, Ricardo _edir. _914650 |
|
| 700 | 1 |
_aOkuno, Hirotsugu _ecodir. _937794 |
|
| 710 | 2 |
_aUniversidad Autónoma de Baja California. _bInstituto de Ingeniería |
|
| 856 | 4 |
_uhttps://drive.google.com/file/d/1jUWURFzAfflbH7JzGXP1qUD80Qc8-kcS/view?usp=sharing _zTesis digital |
|
| 942 | _cTESIS | ||
| 999 |
_c272379 _d272378 |
||