Properties of a high-dimensional space and operations defined for high-dimensional vectors allow encoding the whole scene into a high-dimensional vector with the preservation of the structure. We use the Vector Symbolic Architecture to represent the elements of the Sign-Based World Model on a computational level. The Sign-Based World Model represents information about a scene depicted on an input image in a structured way and grounds abstract objects in an agent’s sensory input. The Vector Semiotic Model combines the advantages of a Semiotic Approach implemented in the Sign-Based World Model and Vector Symbolic Architectures. In this paper, we propose a Vector Semiotic Model as a possible solution to the symbol grounding problem in the context of Visual Question Answering. The findings should encourage further testing of parity processing in a wider variety of animals to inform on its potential biological roots, evolutionary drivers, and potential technology innovations for concept processing. We discuss the possible mechanisms or learning processes allowing bees to perform this categorization task, which range from numeric explanations, such as counting, to pairing elements and memorization of stimuli or patterns. This study thus demonstrates that a task, previously only shown in humans, is accessible to a brain with a comparatively small numbers of neurons. While the simple neural network is not directly based on the biology of the honeybee brain, it was created to determine if simple systems can replicate the parity categorization results we observed in honeybees.
We use this information to construct a neural network consisting of five neurons that can reliably categorize odd and even numerosities up to 40 elements. We show that free-flying honeybees can visually acquire the capacity to differentiate between odd and even quantities of 1–10 geometric elements and extrapolate this categorization to the novel numerosities of 11 and 12, revealing that such categorization is accessible to a comparatively simple system. Odd and even numerical processing is known as a parity task in human mathematical representations, but there appears to be a complete absence of research exploring parity processing in non-human animals. Categorization of abstract concepts can be essential to how we understand complex information. The relative simplicity of the bee brain compared to large mammalian brains enables learning tasks, such as categorization, that can be mimicked by simple neural networks. The honeybee has emerged as a valuable comparative model which exhibits some cognitive-like behaviors.
Creating technology based on humans is challenging and costly as human brains and cognition are complex. Ó2013, Proceedings of the Royal Society B: Biological Sciences, The Royal Society, adopted with permission from Avarguès-Weber and Giurfa (2013).Ī frequent question as technology improves and becomes increasingly complex, is how we enable technological solutions and models inspired by biological systems. Asterisks ( * ) indicate cases where the percentage of correct choices was significantly different from 50%. Transfer tests 2–4 demonstrated that bees also learned that the stimuli had to present two different images.
In transfer test 1, bees transferred their choice to unknown stimuli that presented the same spatial relation even though the stimuli belonged to a different sensory modality. In transfer test 1, correct choices correspond to the selection of the spatial relation that had previously yielded a reward in transfer tests 2, 3 and 4, the term refers to the selection of the appropriate stimulus when presented with 2 different images. Thirty trials were performed for each test. (B) Four transfer tests used to assess learned concepts. The results of transfer tests for the above–below relation are shown. A) Bees were trained in a maze to choose between stimuli presenting two different patterns (group 1) or two differently colored discs (group 2) in an above–elow (or right–left) relation depending on the group of bees.
0 kommentar(er)
