Visual object recognition has been extensively studied in both neuroscience and computer vision. Recently, the most popular class of artificial systems for this task, deep convolutional neural networks (CNNs), has been shown to provide excellent models for its functional analogue in the brain, the ventral stream in visual cortex. This has prompted questions on what, if any, are the common principles underlying the reformatting of visual information as it flows through a CNN or the ventral stream. Here we consider some prominent statistical patterns that are known to exist in the internal representations of either CNNs or the visual cortex and look for them in the other system. We show that intrinsic dimensionality (ID) of object representations along the rat homologue of the ventral stream presents two distinct expansion-contraction phases, as previously shown for CNNs. Conversely, in CNNs, we show that training results in both distillation and active pruning (mirroring the increase in ID) of low- to middle-level image information in single units, as representations gain the ability to support invariant discrimination, in agreement with previous observations in rat visual cortex. Taken together, our findings suggest that CNNs and visual cortex share a similarly tight relationship between dimensionality expansion/reduction of object representations and reformatting of image information.

Dynamical systems theory has helped brain scientists to cope better with brain complexity. In this paper, we proposed a novel approach to include uncertainty in dynamical system describing brain function such as one neuron or coupled neurons. Fuzzy dynamical systems represented by a set of fuzzy differential inclusions (FDI) are very convenient tools for modeling and simulation of various uncertain systems. We used fuzzy differential inclusion in modeling neural responses in several types of neurons. We showed that our results are very similar to real experimental data showing variability in neural responses. Further, we have shown that FDI has advantage in comparison with modeling uncertainty in neural systems with stochastic differential equations (SDEs).

Neural system that controls movement and posture is a highly nonlinear complex system. Its adaptability and easy accommodation to changes in environment and task specifications make it an ideal system. In this paper, the muscle control system from spinal cord to muscle displacement has been studied. At first, a detailed nonlinear model is simulated in Simulink based on an already developed work. Then, three system identification techniques are examined to estimate the behavior of this complex system. The first one is based on popular linear ARX model. Then, the system is modeled by NARX neural network (Nonlinear Autoregressive Network with Exogenous Inputs) which has a powerful structural network in modeling dynamical systems. Finally, a new method of modeling using combined NARX and ARX structure is proposed in which ARX gets the linear part of the system and the NARX picks up the nonlinearities. The simulation results demonstrate the superiority of the latter method with respect to other examined approaches.