Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on distillation-based approaches in two-stage networks; the most-common strategy employed in contemporary continual object detection work.Distillation aims to transfer the knowledge of a model trained on previous tasks -- the teacher -- to a new model -- the student -- while it learns the new task. We show that this works well for the region proposal network, but that wrong, yet overly confident teacher predictions prevent student models from effective learning of the classification head. Our analysis provides a foundation that allows us to propose improvements for existing techniques by detecting incorrect teacher predictions, based on current ground-truth labels, and by employing an adaptive Huber loss as opposed to the mean squared error for the distillation loss in the classification heads. We evidence that our strategy works not only in a class incremental setting, but also in domain incremental settings, which constitute a realistic context, likely to be the setting of representative real-world problems.

We propose a federated learning method with weighted nodes in which the weights can be modified to optimize the model's performance on a separate validation set. The problem is formulated as a bilevel optimization where the inner problem is a federated learning problem with weighted nodes and the outer problem focuses on optimizing the weights based on the validation performance of the model returned from the inner problem. A communication-efficient federated optimization algorithm is designed to solve this bilevel optimization problem. Under an error-bound assumption, we analyze the generalization performance of the output model and identify scenarios when our method is in theory superior to training a model only locally and to federated learning with static and evenly distributed weights.

The most prominent tasks in emotion analysis are to assign emotions to texts and to understand how emotions manifest in language. An observation for NLP is that emotions can be communicated implicitly by referring to events, appealing to an empathetic, intersubjective understanding of events, even without explicitly mentioning an emotion name. In psychology, the class of emotion theories known as appraisal theories aims at explaining the link between events and emotions. Appraisals can be formalized as variables that measure a cognitive evaluation by people living through an event that they consider relevant. They include the assessment if an event is novel, if the person considers themselves to be responsible, if it is in line with the own goals, and many others. Such appraisals explain which emotions are developed based on an event, e.g., that a novel situation can induce surprise or one with uncertain consequences could evoke fear. We analyze the suitability of appraisal theories for emotion analysis in text with the goal of understanding if appraisal concepts can reliably be reconstructed by annotators, if they can be predicted by text classifiers, and if appraisal concepts help to identify emotion categories. To achieve that, we compile a corpus by asking people to textually describe events that triggered particular emotions and to disclose their appraisals. Then, we ask readers to reconstruct emotions and appraisals from the text. This setup allows us to measure if emotions and appraisals can be recovered purely from text and provides a human baseline. Our comparison of text classification methods to human annotators shows that both can reliably detect emotions and appraisals with similar performance. Therefore, appraisals constitute an alternative computational emotion analysis paradigm and further improve the categorization of emotions in text with joint models.

A high school in Michigan is the first private school in the state to use artificial intelligence to detect guns as part of its security system - amid the country's epidemic of school shootings. Lansing Catholic High School is using state funds to pay for a video analytics platform from a company called ZeroEyes that builds AI systems. ZeroEyes' technology is layered onto the school's existing video security equipment. AI and computer vision then work in concert with existing 3D satellite maps of a building - so that when a gun is seen, the exact location lights up to let officials know where the shooter is located. The real-time AI alert system is meant to prevent gun violence.

I sat out Friday's big Tesla AI event. I was actually looking forward to seeing what the company had cooked up after months of teasing, but a combination of rogue stomach virus and the most inconvenient event timing (Friday at 9:15 PM EDT) outside of something held on the other side of the world meant I had to watch the whole thing over the weekend. I'm not sure one can call Optimus "disappointing," exactly. Disappointing implies higher expectations than I think most of us had going into the thing. Elon Musk has largely proven himself to be a great hype man and self-promoter over the years, but in the lead-up to last week's official unveiling, I didn't encounter many serious roboticists who believed we would see much more than what Tesla showed.

Spark Machine Learning Project (Employee Attrition Prediction) for beginners using Databricks Notebook (Unofficial) (Community edition Server) In this Data science Machine Learning project, we will create Employee Attrition Prediction Project using Decision Tree Classification algorithm one of the predictive models.

The Chicago Urban League is partnering with ILLInet RECOVER in an effort to learn more about how COVID 19 is affecting our community.

I did a startup in 1998 by applying AI to the lead generation and qualification problem. It was early. The data was not yet rich enough. Now, the data is there. Can the problem finally be solved at the right level of sophistication? Sramana Mitra: Let's go to the very beginning of your journey. Where were you born and raised? Jonathan Spier: I'm a California guy raised in San Diego. I came up here to go to school at Berkeley. I was never able to escape again. Sramana Mitra: What did you do after Berkeley? Jonathan Spier: I went briefly into consulting and then I landed at a company called Ariba. I was the number 85 employee. Within a few years, we were 3,500 people. It was a fun place to be. Sramana Mitra: We have the Ariba case study. Keith Krach was on the series. Jonathan Spier: He was a great leader. That whole team was amazing. I was the youngest person they hired. It was a really senior team they had by the time I joined. I got pretty much hooked on growth

Scientific knowledge bases [16, 23], a collection of structured and verified research results that consists of various numeric, word-oriented, or image-organized data, emerge in this context and bring entirely new approaches and opportunities to scientific research. Researchers in many disciplines uses AI techniques and the scientific knowledge bases, often constructed from the published literature, to drive scientific discoveries [38, 45, 46], such as Geoscience [10, 64], Medicine [9], Biology [3], Chemistry [50]. The rapid development of AI and data science has further promoted the development of scientific knowledge base [26, 42]. For example, AlphaFold [27], which uses Protein Data Bank [63] as input data, can accurately predict protein structure and greatly promote the development of biological and medical research [12, 39]. Although successful research examples illustrate the importance of scientific knowledge bases for scientific research in the data explosive age, there are still many challenges in the composition of the scientific knowledge base and the construction process due to their characteristics. The characteristic of a scientific knowledge base composition is that it is described around one type of scientific entity. For example, "sample" is a general type of scientific entity. The data contained are the values and sources of the relevant attributes of the scientific entity. The current process of constructing a scientific knowledge base includes four main steps:literature collection, entity and attribute extraction, entity linking, and data storage (see Figure 2).

In this paper, we present InferES - an original corpus for Natural Language Inference (NLI) in European Spanish. We propose, implement, and analyze a variety of corpus-creating strategies utilizing expert linguists and crowd workers. The objectives behind InferES are to provide high-quality data, and, at the same time to facilitate the systematic evaluation of automated systems. Specifically, we focus on measuring and improving the performance of machine learning systems on negation-based adversarial examples and their ability to generalize across out-of-distribution topics. We train two transformer models on InferES (8,055 gold examples) in a variety of scenarios. Our best model obtains 72.8% accuracy, leaving a lot of room for improvement. The "hypothesis-only" baseline performs only 2%-5% higher than majority, indicating much fewer annotation artifacts than prior work. We find that models trained on InferES generalize very well across topics (both in- and out-of-distribution) and perform moderately well on negation-based adversarial examples.