An inferior temporal cortex model
Download as PPTX, PDF0 likes69 views
This document describes a neural network model that aims to simulate object recognition in the inferior temporal cortex. The model processes visual information through two pathways like the biological system. It uses a self-organizing map with radial basis function modules to classify 2D and 3D objects. For 3D objects, it adds a preprocessing module that emulates early visual areas, applying Gabor filters and position-invariant detectors to images divided into overlapping patches. The network was trained to recognize spherical and spiky 3D objects presented at different rotations.
An inferior temporal cortex model
- 1. An Inferior Temporal Cortex Model for Object Recognition and Classification1 Fernando Jesús García Hípola – Taller de RRNN
- 2. Introduction • Aim of the Study: Simulating Temporal Cortex 3D object classification through a NN that imitates it. • Virtual information is processed in two major parallel pathways: the Dorsal and the Ventral • V1, V2, V4 • Inferior Temporal Cortex (IT)
- 3. Biological Process • Retinotopic Organization Imagen V1: Características básicas V4: Características complejas (Smaller parts of Larger Objects) TE: Columnar Organization
- 5. 1 • Inicialización de los pesos wi 2 • Presentación en cada iteración un patrón de entrada x(t) 3 • Determinar similitud entre pesos de cada neurona y la entrada 4 • Determinar Neurona Ganadora (Mayor similitud -> Menor error) 5 • Actualización pesos de la ganadora y sus vecinas (f(x) de vecindad) 6 • Volver al paso 2 si no se ha alcanzado nº máximo de iteraciones, Si no FIN
- 6. Kohonen SOM Los Pesos se comparan con el vector de entrada: Gana la Neurona de la 2ª capa más parecida (min error entre sus pesos y la entrada) Se actualizan los pesos según una función de proximidad para asegurar la vecindad de las clases (Preservar Topología)
- 7. mnSOM • Kohonen SOM only can deal with vectors imputs. • Tukunawa & Furukawa -> mnSOM replace SOM imput vectors by functional modules
- 8. mnSom with RBF Network Modules • Radial Basis Function Neural Networks • Advantages for Image Recognition: No need of an Additional Additional Algotithm for avoiding local minima The network leans to store the objects representation in the inner center The use of RBF is more neurophysiologically plausible
- 9. The NN for Image Recognition • 10 objects as image input, in different degree of rotation: 3 objects with 5 straight segments. 3 objects with 4 straight segments. 4 objects with 3 straight segments.
- 10. 4. Adaptative Process: All the weights and centers within the modules are updated following the back-propagation algorithm 3. Cooperative Process The Weights are calculated by the neighborhood function 2. Competitive Process The module that minimizes the error is the winner. 1. Calculating Process Random initialization of weights and calculate all outputs for all the imputs in a single RBF unit
- 14. The NN for Image Recognition for 3D Objects • The previous hybrid NN works well for simple 2D images, but... What about 3D images? • Solution: Adding a pre-processing Module emuleting V1, V2, V3 and IT biological neural areas, by processing layers: A retinal image is divided into small overlapping patches The patterns are filtered through a layer (S1) of Gabor filters. Position invariant detectors
- 15. Galbor Filter
- 16. The NN for Image Recognition for 3D Objects • 43D-Objects: Spherical objects and Spiky objects • Objects were presented to the NN in projections at each 10º rotation • Training: 200 epochs. • Results follow: similarity between objects and similarity between the different views of the same object