In this paper, we study how to use the number of spike signals in a macaque's motor cortex to estimate the position of its finger movement. First, we analyze the time correlation of a traditional state space model (SSM) and derive a convolutional space model (CSM) to decode the movement position of the macaque finger. Compared with the traditional model, the model can correlate the current moment state with the previous moment. In addition, we have improved the original SSM model using the CSM model. In its observation equation, the number of spike signals at one is expanded to the number of spike signals at multiple previous moments. In this way, the current time state in the improved model can be related to the number of spike signals at a plurality of previous times. In the experiment, a group of public data are used to validate the decoding performance of the model, and a least squares, a batch recursive least squares, and a gradient descent algorithms are used to train the model. The experimental results show that the decoding error of the CSM model and the improved SSM model is smaller than that of the traditional model, and thus, they have a better decoding accuracy. The results show that the CSM model has improved about 11.7% in x-axis decoding error performance than the traditional models.

In this paper, we will study the problem that the location of a macaque's moving finger is decoded through neuron spike signals in its motor cortex. In traditional neural decoding methods, supervised learning is more popular because their decoding accuracy could be guaranteed. However, this paper proposes a weak supervised learning (WSL) method to decode the location of a macaque's moving finger and an unsupervised deep learning model, generative adversarial network (GAN) is introduced to optimize a training model and ultimately achieve an accurate estimation of the finger movement trajectory. In experiments, we use public data to evaluate the decoding performance of the proposed method. The experimental results show that this WSL method has higher accuracy of the location decoding.

Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs) have played a significant role as tools for mining the core features of complex data. However, most methods often overlook the dynamic generation process of neural data, such as hierarchical brain's visual data, within the brain's structure. In the decoding of brain's visual data, two main paradigms are 'fine-grained decoding tests' and 'rough-grained decoding tests', which we define as focusing on a single brain region and studying the overall structure across multiple brain regions, respectively. In this paper, we mainly use the Visual Coding Neuropixel dataset from the Allen Brain Institute, and the hierarchical information extracted from some single brain regions (i.e., fine-grained decoding tests) is provided to the proposed method for studying the adaptive topological decoding between brain regions, called the Adaptive Topological Vision Transformer, or AT-ViT. In numerous experiments, the results reveal the importance of the proposed method in hierarchical networks in the visual tasks, and also validate the hypothesis that "the hierarchical information content in brain regions of the visual system can be quantified by decoding outcomes to reflect an information hierarchy." Among them, we found that neural data collected in the hippocampus can have a random decoding performance, and this negative impact on performance still holds significant scientific value.

Comprehending how the brain interacts with the external world through generated neural data is crucial for determining its working mechanism, treating brain diseases, and understanding intelligence. Although many theoretical models have been proposed, they have thus far been difficult to integrate and develop. In this study, we were inspired in part by grid cells in creating a more general and robust grid module and constructing an interactive and self-reinforcing cognitive system together with Bayesian reasoning, an approach called space-division and exploration-exploitation with grid-feedback (Grid-SD2E). Here, a grid module can be used as an interaction medium between the outside world and a system, as well as a self-reinforcement medium within the system. The space-division and exploration-exploitation (SD2E) receives the 0/1 signals of a grid through its space-division (SD) module. The system described in this paper is also a theoretical model derived from experiments conducted by other researchers and our experience on neural decoding. Herein, we analyse the rationality of the system based on the existing theories in both neuroscience and cognitive science, and attempt to propose special and general rules to explain the different interactions between people and between people and the external world. What's more, based on this framework, the smallest computing unit is extracted, which is analogous to a single neuron in the brain.