A temporal neural network model for object recognition using a biologically plausible decision making layer
This work addresses the gap in biologically plausible models for object recognition that account for processing time, which is incremental as it builds on existing spiking HMAX methods.
The authors tackled the problem of modeling both recognition accuracy and processing time in object recognition by proposing a biologically plausible model that uses temporal feature extraction and an accumulation-to-bound decision layer. The model improved accuracy over the classic spiking HMAX and predicted human response times in a psychophysics task.
Brain can recognize different objects as ones that it has experienced before. The recognition accuracy and its processing time depend on task properties such as viewing condition, level of noise and etc. Recognition accuracy can be well explained by different models. However, less attention has been paid to the processing time and the ones that do, are not biologically plausible. By extracting features temporally as well as utilizing an accumulation to bound decision making model, an object recognition model accounting for both recognition time and accuracy is proposed. To temporally extract informative features in support of possible classes of stimuli, a hierarchical spiking neural network, called spiking HMAX is modified. In the decision making part of the model the extracted information accumulates over time using accumulator units. The input category is determined as soon as any of the accumulators reaches a threshold, called decision bound. Results show that not only does the model follow human accuracy in a psychophysics task better than the classic spiking HMAX model, but also it predicts human response time in each choice. Results provide enough evidence that temporal representation of features are informative since they can improve the accuracy of a biological plausible decision maker over time. This is also in line with the well-known idea of speed accuracy trade-off in decision making studies.