We study the use of parametric building information modeling (BIM) to automatically generate training data for artificial neural networks (ANNs) to recognize building objects in photos. Teaching artificial intelligence (AI) machines to detect building objects in images is the foundation toward AI-assisted semantic 3D reconstruction of existing buildings. However, there exists the challenge of acquiring training data which is typically human-annotated, that is, unless a computer machine can generate high-quality data to train itself for a certain task. In that vein, we trained ANNs solely on realistic computer-generated images of 3D BIM models which were parametrically and automatically generated using the BIMGenE program. The ANN training result demonstrated generalizability and good semantic segmentation on a test case as well as arbitrary photos of buildings that are outside the range of the training data, which is significant for the future of training AI with generated data for solving real-world architectural problems.

Consider a learner that wants to predict the next day's temperature range at a given location based on inputs such as the current day's temperature range, humidity, atmospheric pressure, precipitation, wind speed, solar radiation, location, and time of year. In our model, this learner is tested daily. On a given day, the learner gets inputs for that day, which it uses to output a prediction for the next day's temperature range; when the next day arrives, it sees the correct temperature range, then uses this feedback to update future predictions. As this is repeated, the learner accumulates information to help it make better predictions. A natural question arises: can the learner guarantee that its predictions become better over time, and if so, how quickly? We investigate a model of online learning of real-valued functions previously studied in [9, 12, 13, 1, 10, 11] where an algorithm A learns a real-valued function f from some class F in trials. Past research on this model focused on functions of one input, for example, predicting the temperature range solely based on the time of year. The research showed that, as long as the function is sufficiently smooth, the learner can become a good predictor fairly rapidly. Suppose that F consists of functions f: S R for some set S, and fix some f F. In each trial t = 0,...,m, A receives an input s

Process monitoring and control are essential in modern industries for ensuring high quality standards and optimizing production performance. These technologies have a long history of application in production and have had numerous positive impacts, but also hold great potential when integrated with Industry 4.0 and advanced machine learning, particularly deep learning, solutions. However, in order to implement these solutions in production and enable widespread adoption, the scalability and transferability of deep learning methods have become a focus of research. While transfer learning has proven successful in many cases, particularly with computer vision and homogenous data inputs, it can be challenging to apply to heterogeneous data. Motivated by the need to transfer and standardize established processes to different, non-identical environments and by the challenge of adapting to heterogeneous data representations, this work introduces the Domain Adaptation Neural Network with Cyclic Supervision (DBACS) approach. DBACS addresses the issue of model generalization through domain adaptation, specifically for heterogeneous data, and enables the transfer and scalability of deep learning-based statistical control methods in a general manner. Additionally, the cyclic interactions between the different parts of the model enable DBACS to not only adapt to the domains, but also match them. To the best of our knowledge, DBACS is the first deep learning approach to combine adaptation and matching for heterogeneous data settings. For comparison, this work also includes subspace alignment and a multi-view learning that deals with heterogeneous representations by mapping data into correlated latent feature spaces. Finally, DBACS with its ability to adapt and match, is applied to a virtual metrology use case for an etching process run on different machine types in semiconductor manufacturing.

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

In Bayesian machine learning and statistics, the central object of interest is the posterior distribution found by Bayesian inference--combining prior beliefs with observations according to Bayes' rule. In simple cases, such as in conjugate models, this can be done exactly. But, general (nonconjugate) models require approximate inference techniques such as Monte Carlo or variational inference. These have complementary strengths and weaknesses, hence the most appropriate choice is application dependent. We focus on variational inference, which is on the one hand not guaranteed to be asymptotically exact but is on the other hand computationally efficient and scalable to high-dimensional models and large datasets.

There is a lot of excitement around AI. Recently there has been an incredible amount of buzz around the demos of models like ChatGPT and Dall-E-2. As impressive as these systems are, I think it becomes increasingly important to keep a level head, and not get carried away in a sea of excitement. The following videos/lectures are more focused on how to think about data science projects, and how to attack a problem. I've found these lectures to be highly impactful in my career and enabled me to build effective and practical solutions that fit the exact needs of the companies I've worked for.

This course covers the theoretical foundation for different techniques associated with supervised machine learning models. In addition, a business case study is defined to guide participants through all steps of the analytical life cycle, from problem understanding to model deployment, through data preparation, feature selection, model training and validation, and model assessment. A series of demonstrations and exercises is used to reinforce the concepts and the analytical approach to solving business problems. This course uses Model Studio, the pipeline flow interface in SAS Viya that enables you to prepare, develop, compare, and deploy advanced analytics models. You learn to train supervised machine learning models to make better decisions on big data.

SINGAPORE - Teachers in Singapore say they will likely have to move from assignments requiring regurgitation to those that require greater critical thinking, to stay ahead in the fight against plagiarism. This comes on the back of the rise of ChatGPT, an intelligent chatbot that is able to spin essays and solve mathematical equations in seconds. ChatGPT, developed by San Francisco research firm OpenAI, is being talked about as a major step forward in artificial intelligence (AI), especially its latest version released in November. Simple and free of charge – for now – the chatbot has prompted some schools to start thinking of ways to mitigate cheating, ahead of students' return to schools. ChatGPT's ability to break down complicated concepts into simple language and respond to follow-up questions logically has raised concerns over whether existing plagiarism detection software used in schools, such as Turnitin, can sniff out text drafted by bots.

Hubel and Wiesel's research in the 1950s and 1960s showed that cat visual cortices include neurons that react to tiny parts of the visual field separately. The region of visual space within which visual inputs impact the firing of a single neuron is known as its receptive field while the eyes are not moving. Neighboring cells have receptive fields that are comparable and overlap. The size and location of receptive fields vary consistently across the cortex to generate a full map of visual space. The contralateral visual field is represented by the cortex in each hemisphere.

Today, I am going to talk about how artificial intelligence (AI), machine learning, and deep learning are helping in the development of augmented reality (AR) and virtual reality (VR) technology. First of all, let's start with a brief overview of what these technologies are. Artificial intelligence is a branch of computer science that deals with the development of intelligent systems that can simulate human-like behavior. Machine learning, on the other hand, is a subset of AI that involves the use of algorithms and statistical models to enable computers to learn and improve their performance without being explicitly programmed. Deep learning is a subfield of machine learning that involves the use of artificial neural networks to model high-level abstractions in data.