Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is investigated. The core challenge is framed as protecting previously acquired representations from being catastrophically forgotten. However, comparison of individual methods is nevertheless performed in isolation from the real world by monitoring accumulated benchmark test set performance. The closed world assumption remains predominant, i.e. models are evaluated on data that is guaranteed to originate from the same distribution as used for training. This poses a massive challenge as neural networks are well known to provide overconfident false predictions on unknown and corrupted instances. In this work we critically survey the literature and argue that notable lessons from open set recognition, identifying unknown examples outside of the observed set, and the adjacent field of active learning, querying data to maximize the expected performance gain, are frequently overlooked in the deep learning era. Hence, we propose a consolidated view to bridge continual learning, active learning and open set recognition in deep neural networks. Finally, the established synergies are supported empirically, showing joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, while exhibiting robust open world application.

Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for continual-learning systems to encounter such unseen concepts, the corresponding literature appears to nonetheless focus primarily on alleviating catastrophic interference with learned representations. In this work, we introduce a probabilistic approach that connects these perspectives based on variational inference in a single deep autoencoder model. Specifically, we propose to bound the approximate posterior by fitting regions of high density on the basis of correctly classified data points. These bounds are shown to serve a dual purpose: unseen unknown out-of-distribution data can be distinguished from already trained known tasks towards robust application. Simultaneously, to retain already acquired knowledge, a generative replay process can be narrowed to strictly in-distribution samples, in order to significantly alleviate catastrophic interference.

Artificial intelligence (AI) and digital technology provide extensive possibilities for education. But focusing only on their implementation does not address the challenges associated with them and they may even have a negative impact on learners. So far, the disciplines of psychology and computer science have not provided a theoretical framework for the competence needed to develop and use AI and digital technology in education in order to prepare learners for successful participation in modern societies. The main aim of this paper is to theoretically specify competent use of AI and digital technology in education and to provide a standardized instrument to evaluate courses that teach this competence. Therefore, we (a) combine theoretical contributions from both scientific disciplines to formulate a theoretical framework with four levels for the “Competence to Use Artificial Intelligence and Digital Technology in Educational Processes” (AIEDTEC competence), (b) introduce a questionnaire to evaluate courses that teach AIEDTEC competence, and (c) present results regarding its psychometric properties ($N=240$). The questionnaire showed good to very good psychometric properties and the assumed factor structure was supported by confirmatory factor analyses. The paper connects research on systems thinking and learning and instruction with recent developments regarding AI and digital technology and thereby provides an essential base for creating effective, modern, and safe learning environments in the future as well as a psychometric evaluation instrument.

Plants are constantly exposure to pathogens such as virus, bacteria and fungi. Plant diseases caused by pathogens lead significant crop yield loss globally. Numerous researchers have been studying how to reduce the damage of plant diseases. Plant disease has long been one of the major threats to agriculture security in India because it dramatically reduces the crop yield and compromises its quality. Pests and Diseases results in the destruction of crops or part of the plant resulting in decreased food production leading to food insecurity. Accurate and precise diagnosis of diseases has been a significant challenge. Traditionally, identification of plant diseases has relied on human annotation by visual inspection. Plant diseases affect the growth of their respective species; therefore their early identification is very important. Modern technological approaches such as machine learning and deep learning algorithm have been employed to increase the recognition rate and the accuracy of the results. Various researches have taken place under the field of machine learning for plant disease detection and diagnosis, such traditional machine learning approach being random forest, artificial neural network, support vector machine(SVM), fuzzy logic, K-means method, Convolutional neural networks etc. In this paper a comparative study on machine learning techniques for plant disease detection is performed. In this survey it observed that Convolutional Neural Network gives high accuracy and detects more number of diseases of multiple crops.