Deep learning algorithms have recently gained significant attention due to their impressive performance.

Deep learning algorithms have recently gained significant attention due to their impressive performance.

Understanding and manipulating concrete and abstract concepts is fundamental to human intelligence. Yet, they remain challenging for artificial agents. This paper introduces a multimodal generative approach to high order abstract concept learning, which integrates visual and categorical linguistic information from concrete ones. Our model initially grounds subordinate level concrete concepts, combines them to form basic level concepts, and finally abstracts to superordinate level concepts via the grounding of basic-level concepts. We evaluate the model language learning ability through language-to-visual and visual-to-language tests with high order abstract concepts. Experimental results demonstrate the proficiency of the model in both language understanding and language naming tasks.

Ontology-based clustering has gained attention in recent years due to the potential benefits of ontology. Current ontology-based clustering approaches have mainly been applied to reduce the dimensionality of attributes in text document clustering. Reduction in dimensionality of attributes using ontology helps to produce high quality clusters for a dataset. However, ontology-based approaches in clustering numerical datasets have not been gained enough attention. Moreover, some literature mentions that ontology-based clustering can produce either high quality or low-quality clusters from a dataset. Therefore, in this paper we present a clustering approach that is based on domain ontology to reduce the dimensionality of attributes in a numerical dataset using domain ontology and to produce high quality clusters. For every dataset, we produce three datasets using domain ontology. We then cluster these datasets using a genetic algorithm-based clustering technique called GenClust++. The clusters of each dataset are evaluated in terms of Sum of Squared-Error (SSE). We use six numerical datasets to evaluate the performance of our ontology-based approach. The experimental results of our approach indicate that cluster quality gradually improves from lower to the higher levels of a domain ontology.

Artificial intelligence (AI) is crucial to combat the spread of misinformation and propaganda on the internet. AI is able to analyze and quantify an enormous amounts of information generated daily on a scale that's impossible for humans, ultimately, it's up to us to be part of the process of fact-checking to inform people worldwide. In 2021, the risk of a global pandemic suddenly became a new reality for all and everybody. We are systematically fed by biased, mis- and dis- information. The big tech digital platforms such as Google, Facebook, Baidu or Tencent should do more to tackle fake news and cyber propaganda.

Interpretability remains one of the biggest challenges of modern deep learning applications. The recent advancements in computation models and deep learning research have enabled the creation of highly sophisticated models that can include thousands of hidden layers and tens of millions of neurons. While its relatively simple to create incredibly advanced deep neural network models, its understanding how those models create and use knowledge remains a challenge. Recently, researchers from the Google Brain team published a paper proposing a new method called Concept Activation Vectors(CAVs) that takes a new angle to the interpretability of deep learning models. To understand the CAV technique, it is important to understand the nature of the interpretability challenge in deep learning models.

We propose revisions to the research agenda in Automated Planning. The proposal is based on a review of the role of the Planning Domain Definition Language (PDDL) in the activities of the AI planning community and the impact of PDDL on parts of its research agenda. We specifically show how specific properties of PDDL have impacted research on planning, by putting emphasis on certain research topics and complicating others. We argue that the development of more advanced modeling languages would be — analogously to the impact PDDL has had — a low overhead and smooth route for the ICAPS community shift its research focus to increasingly promising and relevant research topics.