This literature review provides a comprehensive analysis of the functional morphology and paleoecology of Pteranodon, a prominent genus of Pterosaur from the Late Cretaceous period. By synthesizing recent research findings with classic studies, this paper elucidates the aerodynamic and ecological adaptations of Pteranodon, which was one of the largest pterosaurs to ever soar the skies. The review examines the distinctive cranial features, including its elongated cranial crest and its implications for sexual dimorphism and species identification. Detailed analysis of wing morphology and limb proportions reveals insights into its flight mechanics, suggesting that Pteranodon was adapted for dynamic soaring, leveraging its expansive wingspan for efficient long-distance travel. Additionally, the paper explores Pteranodon's feeding habits and dietary preferences based on dental and jaw structure, indicating a diet primarily consisting of fish and other aquatic prey. The review also integrates fossil evidence with ecological models to reconstruct the paleoenvironment of the Late Cretaceous, highlighting the role of Pteranodon in its ecosystem as both a predator and a competitor. This synthesis not only enhances our understanding of Pteranodon’s physiological and ecological roles but also contributes to broader discussions on pterosaur evolution and behavior.

Continual learning, a crucial facet of machine learning, involves the perpetual acquisition of valuable insights from incoming data, sans the necessity for full dataset access. Esteemed as a fundamental goal in artificial intelligence, continual learning grapples with an enduring challenge—catastrophic forgetting. A proficient model must exhibit adaptability for new data assimilation and robustness to retain existing knowledge. Class-incremental learning (CIL) aids the gradual integration of knowledge from newly introduced classes, forming a universal classifier. However, directly training the model with fresh class instances triggers a problem—forgetting distinguishing features of prior classes, causing a performance decline. Addressing such issues in machine learning, this survey aims to delineate significant challenges, outcomes, and recent advancements, including our contributions to CIL techniques, especially in image classification.