Unsupervised Learning of Biologically Plausible Object Recognition Strategies
نویسندگان
چکیده
Recent psychological and neurological evidence suggests that biological object recognition is a process of matching sensed images to stored iconic memories. This paper presents a partial implementation of (our interpretation of) Kosslyn's biological vision model, with a control system added to it. We then show how reinforcement learning can be used to control and optimize recognition in an unsupervised learning mode, where the result of image matching is used as the reward signal to optimize earlier stages of processing.
منابع مشابه
A Biological Model of Object Recognition with Feature Learning
Previous biological models of object recognition in cortex have been evaluated using idealized scenes and have hard-coded features, such as the HMAX model by Riesenhuber and Poggio [10]. Because HMAX uses the same set of features for all object classes, it does not perform well in the task of detecting a target object in clutter. This thesis presents a new model that integrates learning of obje...
متن کاملConvolutional Spike Timing Dependent Plasticity based Feature Learning in Spiking Neural Networks
Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we present convolutional spike timing dependent plasticity based feature learning with biologically plausible leaky-integrate-and-fire neurons in Spiking Neural Networks (SNNs). W...
متن کاملCoupling of Evolution and Learning to Optimize a Hierarchical Object Recognition Model
A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization methods can help to solve this problem. In this work we compare different evolutionary optimization approaches for a biologically inspired neural vision system: Direct coding versus a biologically more plausible indirect coding usi...
متن کاملStacked Convolutional Auto-Encoders for Hierarchical Feature Extraction
We present a novel convolutional auto-encoder (CAE) for unsupervised feature learning. A stack of CAEs forms a convolutional neural network (CNN). Each CAE is trained using conventional on-line gradient descent without additional regularization terms. A max-pooling layer is essential to learn biologically plausible features consistent with those found by previous approaches. Initializing a CNN ...
متن کاملBody-form and body-pose recognition with a hierarchical model of the ventral stream
When learning to recognize a novel body shape, e.g., a panda bear, we are not misled by changes in its pose. A "jumping panda bear" is readily recognized, despite having no prior visual experience with the conjunction of these concepts. Likewise, a novel pose can be estimated in an invariant way, with respect to the actor’s body shape. These body and pose recognition tasks require invariance to...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000