Concept Learning in Neuromorphic Vision Systems: What Can We Learn from Insects?

Vision systems that enable collision avoidance, localization and navigation in complex and uncertain environments are common in biology, but are extremely challenging to mimic in artificial electronic systems, in particular when size and power limitations apply. The development of neuromorphic electronic systems implementing models of biological sensory-motor systems in silicon is one promising approach to addressing these challenges. Concept learning is a central part of animal cognition that enables appropriate motor response in novel situations by generalization of former experience, possibly from a few examples. These aspects make concept learning a challenging and important problem. Learning methods in computer vision are typically inspired by mammals, but recent studies of insects motivate an interesting complementary research direction. There are several remarkable results showing that honeybees can learn to master abstract concepts, providing a road map for future work to allow direct comparisons between bio-inspired computing architectures and information processing in miniaturized “real” brains. Considering that the brain of a bee has less than 0.01% as many neurons as a human brain, the task to infer a minimal architecture and mechanism of concept learning from studies of bees appears well motivated. The relatively low complexity of insect sensory-motor systems makes them an interesting model for the further development of bio-inspired computing architectures, in particular for resource-constrained applications such as miniature robots, wireless sensors and handheld or wearable devices. Work in that direction is a natural step towards understanding and making use of prototype circuits for concept learning, which eventually may also help us to understand the more complex learning circuits of the human brain. By adapting concept learning mechanisms to a polymorphic computing framework we could possibly create large-scale decentralized computer vision systems, for example in the form of wireless sensor networks.

A Hybrid Genetic Algorithm for Supervised Inductive Learning

A novel algorithm is presented for supervised inductive learning by integrating a genetic algorithm with hot'tom-up induction process.The hybrid learning algorithm has been implemented in C on a personal computer(386DX/40).The performance of the algorithm has been evaluated by applying it to 11-multiplexer problem and the results show that the algorithm's accuracy is higher than the others[5,12, 13].

Visual Superordinate Abstraction for Robust Concept Learning

Concept learning constructs visual representations that are connected to linguistic semantics, which is fundamental to vision-language tasks. Although promising progress has been made, existing concept learners are still vulnerable to attribute perturbations and out-of-distribution compositions during inference. We ascribe the bottleneck to a failure to explore the intrinsic semantic hierarchy of visual concepts, e.g., {red, blue,···} ∈“color” subspace yet cube ∈“shape”. In this paper, we propose a visual superordinate abstraction framework for explicitly modeling semantic-aware visual subspaces(i.e., visual superordinates). With only natural visual question answering data, our model first acquires the semantic hierarchy from a linguistic view and then explores mutually exclusive visual superordinates under the guidance of linguistic hierarchy. In addition, a quasi-center visual concept clustering and superordinate shortcut learning schemes are proposed to enhance the discrimination and independence of concepts within each visual superordinate. Experiments demonstrate the superiority of the proposed framework under diverse settings, which increases the overall answering accuracy relatively by 7.5% for reasoning with perturbations and 15.6% for compositional generalization tests.

Using a Hybrid Genetic Algorithm to Learn Rules From Examples

in this article a novel learning method is proposed,which is a combination of GA and the bottomup induction process. The method has been implemented in a system called KAA,and we evaluate it on a multiplexer problem,which shows the higher predict accuracy even in a noisy environment.

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

Same or different?Abstract relational concept use in juvenile bamboo sharks and Malawi cichlids

Sorting objects and events into categories and concepts is an important cognitive prerequisite that spares an individual the learning of every object or situation encountered in its daily life.Accordingly,specific items are classified in general groups that allow fast responses to novel situations.The present study assessed whether bamboo sharks Chiloscyllium griseum and Malawi cichlids Pseudotropheus zebra can distinguish sets of stimuli(each stimulus consisting of two abstract,geometric objects)that meet two conceptual preconditions,i.e.,(1)"sameness"versus"difference"and(2)a certain spatial arrangement of both objects.In two alternative forced choice experiments,individuals were first trained to choose two different,vertically arranged objects from two different but horizontally arranged ones.Pair discriminations were followed by extensive transfer test experiments.Transfer tests using stimuli consisting of(a)black and gray circles and(b)squares with novel geometric patterns provided conflicting information with respect to the learnt rule"choose two different,vertically arranged objects",thereby investigating(1)the individuals'ability to transfer previously gained knowledge to novel stimuli and(2)the abstract relational concept(s)or rule(s)applied to categorize these novel objects.Present results suggest that the level of processing and usage of both abstract concepts differed considerably between bamboo sharks and Malawi cichlids.Bamboo sharks seemed to combine both concepts-although not with equal but hierarchical prominence-pointing to advanced cognitive capabilities.Conversely,Malawi cichlids had difficulties in discriminating between symbols and failed to apply the acquired training knowledge on new sets of geometric and,in particular,gray-level transfer stimuli.

Effectively Discriminating Fighting Shots in Action Movies

Fighting shots are the highlights of action movies and an effective approach to discriminating fighting shots is very useful for many applications, such as movie trailer construction, movie content filtering, and movie content retrieval. In this paper, we present a novel method for this task. Our approach first extracts the reliable motion information of local invariant features through a robust keypoint tracking computation; then foreground keypoints are distinguished from background keypoints by a sophisticated voting process; further, the parameters of the camera motion model is computed based on the motion information of background keypoints, and this model is then used as a reference to compute the actual motion of foreground keypoints; finally, the corresponding feature vectors are extracted to characterizing the motions of foreground keypoints, and a support vector machine （SVM） classifier is trained based on the extracted feature vectors to discriminate fighting shots. Experimental results on representative action movies show our approach is very effective.