Humans and chimpanzees differ in their cognitive abilities, in particular, in social-cognitive processing;however, the underlying neural mechanisms are still unknown. Based on the theory of predictive coding, we hypot...
详细信息
Humans and chimpanzees differ in their cognitive abilities, in particular, in social-cognitive processing;however, the underlying neural mechanisms are still unknown. Based on the theory of predictive coding, we hypothesize that crucial differences in cognitive processing might arise from aberrant reliance on predictions. We test this hypothesis using a recurrent neural network that integrates sensory information with predictions based on the rules of Bayesian inference. Altering a network parameter, we vary how strongly the network relies on its predictions during development. Our model qualitatively replicates findings from a behavioral study on the drawing ability of human children and chimpanzees. Moderate parameter values replicate the ability of human children to complete drawings by adding missing elements. With weak reliance on predictions, the model's behavior is similar to chimpanzees' behaviors: trained networks can follow existing lines but fail to complete drawings. Furthermore, with a strong reliance on predictions, networks learn more abstract representations of drawings and confuse different trained patterns. An analysis of the internal network representations reveals that an aberrant reliance on predictions affects the formation of attractors in the network. Thus, appropriate reliance on their own predictions in humans may be crucial for developing abstract representations and acquiring cognitive skills.
predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep ...
详细信息
predictive coding, currently a highly influential theory in neuroscience, has not been widely adopted in machine learning yet. In this work, we transform the seminal model of Rao and Ballard (1999) into a modern deep learning framework while remaining maximally faithful to the original schema. The resulting network we propose (PreCNet) is tested on a widely used next frame video prediction benchmark, which consists of images from an urban environment recorded from a car-mounted camera, and achieves state-of-the-art performance. Performance on all measures (MSE, PSNR, SSIM) was further improved when a larger training set (2M images from BDD100k), pointing to the limitations of the KITTI training set. This work demonstrates that an architecture carefully based in a neuroscience model, without being explicitly tailored to the task at hand, can exhibit exceptional performance.
predictive coding is attractive for compression of hyperspectral images onboard of spacecrafts in light of the excellent rate-distortion performance and low complexity of recent schemes. In this letter, we propose a r...
详细信息
predictive coding is attractive for compression of hyperspectral images onboard of spacecrafts in light of the excellent rate-distortion performance and low complexity of recent schemes. In this letter, we propose a rate control algorithm and integrate it in a lossy extension to the CCSDS-123 lossless compression recommendation. The proposed rate algorithm overhauls our previous scheme by being orders of magnitude faster and simpler to implement, while still providing the same accuracy in terms of output rate and comparable or better image quality.
This paper presents a prediction-based image-hiding scheme that embeds secret data into compression codes during image compression. This scheme employs a two-stage structure: a prediction stage and an entropy coding s...
详细信息
This paper presents a prediction-based image-hiding scheme that embeds secret data into compression codes during image compression. This scheme employs a two-stage structure: a prediction stage and an entropy coding stage. The secret data is embedded into the difference values of a given image after the prediction stage is performed. According to the experimental results, the image quality is better than Jpeg-Jsteg and its improved scheme (Inform. Sci. 141 (1-2) (2002) 123). The average image quality of the stego-images in the proposed scheme is greater than 50dB when the hiding capacity is 1 bit per pixel, whereas those values in Jpeg-Jsteg and scheme in Chang et al. (Inform. Sci. 141 (1-2) (2002) 123) are 37.04 and 33.73 dB, respectively. The hiding capacity of the proposed scheme is 65,536 bits when the hiding capacity is I bit per pixel, whereas it is 53,248 bits in scheme (Inform. Sci. 141 (1-2) (2002) 123) and less than 3000 bits in Jpeg-Jsteg. (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.
We introduce two new source coding problems: robust sequential coding and robust predictive coding. For the Gauss-Markov source model with the mean squared error distortion measure, we characterize certain supporting ...
详细信息
We introduce two new source coding problems: robust sequential coding and robust predictive coding. For the Gauss-Markov source model with the mean squared error distortion measure, we characterize certain supporting hyperplanes of the rate region of these two coding problems. Our investigation also reveals an information-theoretic minimax theorem and the associated extremal inequalities.
This paper aims to investigate how adequate cognitive functions for recognizing, predicting, and generating a variety of actions can be developed through iterative learning of action-caused dynamic perceptual patterns...
详细信息
This paper aims to investigate how adequate cognitive functions for recognizing, predicting, and generating a variety of actions can be developed through iterative learning of action-caused dynamic perceptual patterns. Particularly, we examined the capabilities of mental simulation of one's own actions as well as the inference of others' intention because they play a crucial role, especially in social cognition. We propose a dynamic neural network model based on predictive coding which can generate and recognize dynamic visuo-proprioceptive patterns. The proposed model was examined by conducting a set of robotic simulation experiments in which a robot was trained to imitate visually perceived gesture patterns of human subjects in a simulation environment. The experimental results showed that the proposed model was able to develop a predictive model of imitative interaction through iterative learning of large-scale spatio-temporal patterns in visuo-proprioceptive input streams. Also, the experiment verified that the model was able to generate mental imagery of dynamic visuo-proprioceptive patterns without feeding the external inputs. Furthermore, the model was able to recognize the intention of others by minimizing prediction error in the observations of the others' action patterns in an online manner. These findings suggest that the error minimization principle in predictive coding could provide a primal account for the mirror neuron functions for generating actions as well as recognizing those generated by others in a social cognitive context.
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional LSTM (convLSTM) modu...
详细信息
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional LSTM (convLSTM) modules. We introduce a novel rgcLSTM architecture that requires a significantly lower parameter budget than a comparable convLSTM. By using a single multifunction gate, our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, thereby reducing training time and memory requirements. We tested our reduced gate modules within a predictive coding architecture on the moving MNIST and KITTI datasets. We found that our reduced-gate model has a significant reduction of approximately 40% of the total number of training parameters and a 25% reduction in elapsed training time in comparison with the standard convolutional LSTM model. The performance accuracy of the new model was also improved. This makes our model more attractive for hardware implementation, especially on small devices. We also explored a space of 20 different gated architectures to get insight into how our rgcLSTM fits into that space.
predictive coding potentially provides an explanatory model for understanding the neurocognitive mechanisms of psychosis. It proposes that cognitive processes, such as perception and inference, are implemented by a hi...
详细信息
predictive coding potentially provides an explanatory model for understanding the neurocognitive mechanisms of psychosis. It proposes that cognitive processes, such as perception and inference, are implemented by a hierarchical system, with the influence of each level being a function of the estimated precision of beliefs at that level. However, predictive coding models of psychosis are insufficiently constrained-any phenomenon can be explained in multiple ways by postulating different changes to precision at different levels of processing. One reason for the lack of constraint in these models is that the core processes are thought to be implemented by the function of specific cortical layers, and the technology to measure layer specific neural activity in humans has until recently been lacking. As a result, our ability to constrain the models with empirical data has been limited. In this review we provide a brief overview of predictive processing models of psychosis and then describe the potential for newly developed, layer specific neuroimaging techniques to test and thus constrain these models. We conclude by discussing the most promising avenues for this research as well as the technical and conceptual challenges which may limit its application. (c) 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).
An increasing number of human electroencephalography (EEG) studies examining the earliest component of the visual evoked potential, the so-called Cl, have cast doubts on the previously prevalent notion that this compo...
详细信息
An increasing number of human electroencephalography (EEG) studies examining the earliest component of the visual evoked potential, the so-called Cl, have cast doubts on the previously prevalent notion that this component is impermeable to top-down effects. This article reviews the original studies that (i) described the Cl, (ii) linked it to primary visual cortex (V1) activity, and (iii) suggested that its electrophysiological characteristics are exclusively determined by low-level stimulus attributes, particularly the spatial position of the stimulus within the visual field. We then describe conflicting evidence from animal studies and human neuroimaging experiments and provide an overview of recent EEG and magnetoen-cephalography (MEG) work showing that initial V1 activity in humans may be strongly modulated by higher-level cognitive factors. Finally, we formulate a theoretical framework for understanding top-down effects on early visual processing in terms of predictive coding. (C) 2011 Elsevier Ltd. All rights reserved.
predictive coding theories posit that the perceptual system is structured as a hierarchically organized set of generative models with increasingly general models at higher levels. The difference between model predicti...
详细信息
predictive coding theories posit that the perceptual system is structured as a hierarchically organized set of generative models with increasingly general models at higher levels. The difference between model predictions and the actual input (prediction error) drives model selection and adaptation processes minimizing the prediction error. Event-related brain potentials elicited by sensory deviance are thought to reflect the processing of prediction error at an intermediate level in the hierarchy. We review evidence from auditory and visual studies of deviance detection suggesting that the memory representations inferred from these studies meet the criteria set for perceptual object representations. Based on this evidence we then argue that these perceptual object representations are closely related to the generative models assumed by predictive coding theories. (C) 2011 Elsevier B.V. All rights reserved.
暂无评论