Learner-generated drawings by students with mathematical learning difficulties in finishing open number sentences

Although MLD students do not have good mathematical performance in completing addition and subtraction operations of integers, MLD students have suggestive ideas in the form of drawings produced in solving open number sentences questions. This study aims to classify the types and identify changes in the drawing produced by MLD students in solving open number sentences questions. This research method is qualitative with a micro generic study approach to understand students' thinking individually and explore drawing changes in solving open number sentences questions between sessions. The research subjects were 2 out of 20 MLD grade 5 elementary school students who produced the most varied drawings in solving open number sentences questions. Data collection techniques used are giving questions and interviews. The results showed that MLD students produced: discrete object drawings by focusing on the cardinality of the quantity of a number; transitions from objects to the number line by focusing on the magnitude of numbers; partitioning the number line using magnitude reasoning; number sentences; and others using verbal reasoning. Changes in the drawings produced by MLD students between sessions indicate the development of students' understanding towards a better direction in interpreting symbolic representations to visual representations. The results of this study contribute to the theory that although MLD students have low mathematical performance. However, MLD students can produce variations and changes in drawings with rich mathematical idea information representing integer operations.

Dis-Cover AI Minds to Preserve Human Knowledge

Modern AI technologies make use of statistical learners that lead to self-empiricist logic, which, unlike human minds, use learned non-symbolic representations. Nevertheless, it seems that it is not the right way to progress in AI. The structure of symbols—the operations by which the intellectual solution is realized—and the search for strategic reference points evoke important issues in the analysis of AI. Studying how knowledge can be represented through methods of theoretical generalization and empirical observation is only the latest step in a long process of evolution. For many years, humans, seeing language as innate, have carried out symbolic theories. Everything seems to have skipped ahead with the advent of Machine Learning. In this paper, after a long analysis of history, the rule-based and the learning-based vision, we would investigate the syntax as possible meeting point between the different learning theories. Finally, we propose a new vision of knowledge in AI models based on a combination of rules, learning, and human knowledge.

Chapter 17. Logic Tensor Networks: Theory and Applications

The recent availability of large-scale data combining multiple data modalities has opened various research and commercial opportunities in Artificial Intelligence (AI). Machine Learning (ML) has achieved important results in this area mostly by adopting a sub-symbolic distributed representation. It is generally accepted now that such purely sub-symbolic approaches can be data inefficient and struggle at extrapolation and reasoning. By contrast, symbolic AI is based on rich, high-level representations ideally based on human-readable symbols. Despite being more explainable and having success at reasoning, symbolic AI usually struggles when faced with incomplete knowledge or inaccurate, large data sets and combinatorial knowledge. Neurosymbolic AI attempts to benefit from the strengths of both approaches combining reasoning with complex representation of knowledge and efficient learning from multiple data modalities. Hence, neurosymbolic AI seeks to ground rich knowledge into efficient sub-symbolic representations and to explain sub-symbolic representations and deep learning by offering high-level symbolic descriptions for such learning systems. Logic Tensor Networks (LTN) are a neurosymbolic AI system for querying, learning and reasoning with rich data and abstract knowledge. LTN introduces Real Logic, a fully differentiable first-order language with concrete semantics such that every symbolic expression has an interpretation that is grounded onto real numbers in the domain. In particular, LTN converts Real Logic formulas into computational graphs that enable gradient-based optimization. This chapter presents the LTN framework and illustrates its use on knowledge completion tasks to ground the relational predicates (symbols) into a concrete interpretation (vectors and tensors). It then investigates the use of LTN on semi-supervised learning, learning of embeddings and reasoning. LTN has been applied recently to many important AI tasks, including semantic image interpretation, ontology learning and reasoning, and reinforcement learning, which use LTN for supervised classification, data clustering, semi-supervised learning, embedding learning, reasoning and query answering. The chapter presents some of the main recent applications of LTN before analyzing results in the context of related work and discussing the next steps for neurosymbolic AI and LTN-based AI models.

Chapter 11. Neuro-Symbolic Semantic Reasoning

Humans have astounding reasoning capabilities. They can learn from very few examples while providing explanations for their decision-making process. In contrast, deep learning techniques–even though robust to noise and very effective in generalizing across several fields including machine vision, natural language understanding, speech recognition, etc. –require large amounts of data and are mostly unable to provide explanations for their decisions. Attaining human-level robust reasoning requires combining sound symbolic reasoning with robust connectionist learning. However, connectionist learning uses low-level representations–such as embeddings–rather than symbolic representations. This challenge constitutes what is referred to as the Neuro-Symbolic gap. A field of study to bridge this gap between the two paradigms has been called neuro-symbolic integration or neuro-symbolic computing. This chapter aims to present approaches that contribute towards bridging the Neuro-Symbolic gap specifically in the Semantic Web field, RDF Schema (RDFS) and EL+ reasoning and to discuss the benefits and shortcomings of neuro-symbolic reasoning.

A Gradient Harmonic Grammar Account of Nasals in Extended Phonological Words

The article aims at contributing to the long-standing research on the prosodic organization of linguistic elements and the criteria used for identifying prosodic structures. Our focus is on final coronal nasals in function words in Greek and the variability in their patterns of realization before lexical words. Certain nasals coalesce before stops and delete before fricatives, whereas others do not. We propose that this split in the behavior of nasals does not pertain to item-specific prosody because the relevant strings are uniformly prosodified into an extended phonological word (Itô & Mester 2007, 2009). It rather stems from the contrastive activity level of nasals in underlying forms in the spirit of Smolensky & Goldrick’s (2016) Gradient Symbolic Representations; nasals with lower activity coalesce and delete in the respective phonological environments, whereas those with higher activity do not. We show that the proposed analysis captures certain gradient effects that alternative analyses cannot account for.

Joanna I of Anjou (1343–1382)

Joanna I of Anjou (1325–1382), countess of Provence and the fourth sovereign of the Angevin dynasty in south Italy (since 1343), became the heir to the throne of the Kingdom of Sicily, succeeding her grandfather King Robert “the Wise” (1277–1343). The public and official images of the queen and the “symbolic” representations of her power, commissioned by her or by her entourage, contributed to create a new standard in the cultural references of the Angevin iconographic tradition aiming to assimilate models shared by the European ruling class. In particular, the following works of art and architecture will be analyzed: the queen’s portraits carved on the front slabs of royal sepulchers (namely those of her mother Mary of Valois and of Robert of Anjou) and on the liturgical furnishings in the church of Santa Chiara in Naples; the images painted in numerous illuminated manuscripts, in the chapter house of the friars in the Franciscan convent of Santa Chiara in Naples, in the lunette of the church in the Charterhouse of Capri. The church of the Incoronata in Naples does not show, at the present time, any portrait of the queen or explicit reference to Joanna as a patron. However, it is considered the highest symbolic image of her queenship.

Robust wave-feature adaptive heartbeat classification based on self-attention mechanism using a transformer model

Objective: Electrocardiography is a common method for screening cardiovascular diseases. Accurate heartbeat classification assists in diagnosis and has attracted great attention. In this paper, we proposed an automatic heartbeat classification method based on a transformer neural network using a self-attention mechanism. Approach: An adaptive heartbeat segmentation method was designed to selectively focus on the time-dependent representation of heartbeats. A one-dimensional convolution layer was used to embed wave characteristics into symbolic representations, and then, a transformer block using multi-head attention was applied to deal with the dependence of wave-embedding. The model was trained and evaluated using the MIT-BIH arrhythmia database (MIT-DB). To improve the model performance, the model pre-trained on MIT-BIH supraventricular arrhythmia database (MIT-SVDB) was used and fine-tuned on MIT-DB. Main results: The proposed method was verified using the MIT-DB for two groups. In the first group, our method attained F1 scores of 0.86 and 0.96 for the supraventricular ectopic beat (SVEB) class and ventricular ectopic beat (VEB) class, respectively. In the second group, our method achieved an average F1 value of 99.83% and better results than other state-of-the-art methods. Significance: We proposed a novel heartbeat classification method based on a transformer model. This method provides a new solution for real-time electrocardiogram heartbeat classification, which can be applied to wearable devices.

Metaforenanalyse als methode om de betekenis van de verpleegkundig specialist vanuit patiëntperspectief te beschrijven

Metaphor identification in order to describe what meaning patients associate with their experiences with a nurse practitioner To explore interpretations and meanings of individuals’ experiences, it is normal to conduct open in-depth interviews. Asking participants to express their meanings and beliefs through metaphors or other symbolic representations can enhance insight in their experiences. Also it will support those who find it difficult to describe their feelings in words alone. This article describes some methodological considerations, the process of using and analyzing metaphors, and the identified metaphors. The article ends by reflecting on the impact of using metaphors as a way to collect experiences, both from the researcher and participant perspective. Furthermore, we recommend using metaphors or other symbolic representations in future research studying lived experiences and meanings participants associate with these experiences.

Emotional thinking as the foundation of consciousness in artificial intelligence

Current theories of artificial intelligence (AI) generally exclude human emotions. The idea at the core of such theories could be described as ‘cognition is computing’; that is, that human psychological and symbolic representations and the operations involved in structuring such representations in human thinking and intelligence can be converted by AI into a series of cognitive symbolic representations and calculations in a manner that simulates human intelligence. However, after decades of development, the cognitive computing doctrine has encountered many difficulties, both in theory and in practice; in particular, it is far from approaching real human intelligence. Real human intelligence runs through the whole process of the emotions. The core and motivation of rational thinking are derived from the emotions. Intelligence without emotion neither exists nor is meaningful. For example, the idea of ‘hot thinking’ proposed by Paul Thagard, a philosopher of cognitive science, discusses the mechanism of the emotions in human cognition and the thinking process. Through an analysis from the perspectives of cognitive neurology, cognitive psychology and social anthropology, this article notes that there may be a type of thinking that could be called ‘emotional thinking’. This type of thinking includes complex emotional factors during the cognitive processes. The term is used to refer to the capacity to process information and use emotions to integrate information in order to arrive at the right decisions and reactions. This type of thinking can be divided into two types according to the role of cognition: positive and negative emotional thinking. That division reflects opposite forces in the cognitive process. In the future, ‘emotional computing’ will cause an important acceleration in the development of AI consciousness. The foundation of AI consciousness is emotional computing based on the simulation of emotional thinking.