We introduce UltraBots, a system that combines ultrasound haptic feedback and robotic actuation for large-area mid-air haptics for VR. Ultrasound haptics can provide precise mid-air haptic feedback and versatile shape rendering, but the interaction area is often limited by the small size of the ultrasound devices, restricting the possible interactions for VR. To address this problem, this paper introduces a novel approach that combines robotic actuation with ultrasound haptics. More specifically, we will attach ultrasound transducer arrays to tabletop mobile robots or robotic arms for scalable, extendable, and translatable interaction areas. We plan to use Sony Toio robots for 2D translation and/or commercially available robotic arms for 3D translation. Using robotic actuation and hand tracking measured by a VR HMD (e.g., Oculus Quest), our system can keep the ultrasound transducers underneath the user's hands to provide on-demand haptics. We demonstrate applications with workspace environments, medical training, education and entertainment.

Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone feature extractors in downstream tasks. As a main-stream loss function for training deep neural network (DNN) classifiers, the cross entropy loss can easily lead us to find models which demonstrate severe overfitting behavior when no other techniques are used for alleviating it such as data augmentation. In this paper, we prove that the existing cross entropy loss minimization for training DNN classifiers essentially learns the conditional entropy of the underlying data distribution of the dataset, i.e., the information or uncertainty remained in the labels after revealing the input. In this paper, we propose a mutual information learning framework where we train DNN classifiers via learning the mutual information between the label and input. Theoretically, we give the population error probability lower bound in terms of the mutual information. In addition, we derive the mutual information lower and upper bounds for a concrete binary classification data model in $\mbR^n$, and also the error probability lower bound in this scenario. Besides, we establish the sample complexity for accurately learning the mutual information from empirical data samples drawn from the underlying data distribution. Empirically, we conduct extensive experiments on several benchmark datasets to support our theory. Without whistles and bells, the proposed mutual information learned classifiers (MILCs) acheive far better generalization performances than the state-of-the-art classifiers with an improvement which can exceed more than 10\% in testing accuracy.

Most classifiers rely on discriminative boundaries that separate instances of each class from everything else. We argue that discriminative boundaries are counter-intuitive as they define semantics by what-they-are-not; and should be replaced by generative classifiers which define semantics by what-they-are. Unfortunately, generative classifiers are significantly less accurate. This may be caused by the tendency of generative models to focus on easy to model semantic generative factors and ignore non-semantic factors that are important but difficult to model. We propose a new generative model in which semantic factors are accommodated by shell theory's hierarchical generative process and non-semantic factors by an instance specific noise term. We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues. The result is a surprisingly accurate generative classifier, that takes the form of a modified nearest-neighbor algorithm; we term it distance classification. Unlike discriminative classifiers, a distance classifier: defines semantics by what-they-are; is amenable to incremental updates; and scales well with the number of classes.

Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically thought to underlie learning in the brain, the precise neural and synaptic mechanisms by which learning processes improve through experience are not well understood. Here, we present a general-purpose, biologically-plausible meta-learning rule which estimates gradients with respect to the parameters of an underlying learning algorithm by simply running it twice. Our rule may be understood as a generalization of contrastive Hebbian learning to meta-learning and notably, it neither requires computing second derivatives nor going backwards in time, two characteristic features of previous gradient-based methods that are hard to conceive in physical neural circuits. We demonstrate the generality of our rule by applying it to two distinct models: a complex synapse with internal states which consolidate task-shared information, and a dual-system architecture in which a primary network is rapidly modulated by another one to learn the specifics of each task. For both models, our meta-learning rule matches or outperforms reference algorithms on a wide range of benchmark problems, while only using information presumed to be locally available at neurons and synapses. We corroborate these findings with a theoretical analysis of the gradient estimation error incurred by our rule.

Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference trade-off problem between different examples. However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available. In this work, we propose a novel efficient meta-learning algorithm for solving the online continual learning problem, where the regularization terms and learning rates are adapted to the Taylor approximation of the parameter's importance to mitigate forgetting. The proposed method expresses the gradient of the meta-loss in closed-form and thus avoid computing second-order derivative which is computationally inhibitable. We also use Proximal Gradient Descent to further improve computational efficiency and accuracy. Experiments on diverse benchmarks show that our method achieves better or on-par performance and much higher efficiency compared to the state-of-the-art approaches.

Machine learning technology is now so common that you probably use it dozens of times a day without even realizing it. And since it has so many applications, the job prospects are great for anyone with a lot of machine learning experience. We just released a machine learning course on the freeCodeCamp.org YouTube channel that is the perfect place to start your learning journey. Kylie Ying developed this course.

Young scientists want machine learning revolution in Africa Kudzai Mashininga 29 September 2022 Cameroon national Loic Elnathan Tiokou Fangang concluded his masters degree in mathematical sciences at the African Institute for Mathematical Sciences (AIMS) earlier in 2022 and, as he awaits an opportunity to pursue a PhD in machine learning, he believes the dream of the institute's founders – of producing the next Einstein – has already been accomplished. AIMS is a network of six centres of excellence, which are based in South Africa, Senegal, Ghana, Cameroon, Tanzania and Rwanda. Students who join the institute get to work on driving the continent's STEM (science, technology, engineering and mathematics) agenda. The founder of AIMS, South African physicist Neil Turok, in 2008 gave a speech in which he declared his wish that the next Einstein would be from Africa. In an interview with University World News, Fangang said that, each year, AIMS is producing African Einsteins as it invests in its students – and not just by equipping them with mathematical skills.

The idea of including the topic of artificial intelligence in school curricula begins in the far north-east of Italy, specifically from the "Bunarrotti" secondary school in Monfalcone, where Dean Vincenzo Kaiko He also talked about creating a real network of schools that intend to offer educational courses to their students on this subject. Vincenzo Kaiko explains it Data science and artificial intelligence They are scientific disciplines closely related and related to other fields of knowledge such as mathematics, natural sciences, humanities, and economics, which together represent the most interesting frontier of new information and communication technologies. Integration of the study of data science and artificial intelligence into the high school track – Monfalcone School Principal adds It can allow male and female students to gain important basic knowledge in rapidly expanding fields of science and technology, both in terms of broadening their cultural background and in terms of orientation towards university studies. The study of these two disciplines also allows for logical development – mathematical skills, analytical and abstract skills, ability to solve problems and creativity, in an interdisciplinary and mutually enriching relationship both with mathematics, physics and the natural sciences, and with the humanistic disciplines." There are currently four Italian schools that have independently started secondary school curriculum studies with the aim of data science and artificial intelligence: these are Maserati High Schools in Foggera, Volta in Reggio Calabria and Galilei in Trento.

Linear Algebra is usually a prerequisite of machine learning. However, one doesn't need to know all the concepts in linear algebra. In this course, I have compiled together all the important linear algebra concepts that are most frequently used in machine learning. This is the content I taught at Polytechnique Montreal as a refresher on linear algebra for machine learning. Understanding these concepts will help you navigate through an introductory course in machine learning.

This article was made in collaboration with Sean Eugene Chua, an undergraduate student at the University of Toronto who has shared experiences across fields that include data science, programming, and machine learning. By definition, it is when a machine can imitate human behavior and emulate how they think and act. A published paper written by logician Walter Pitts and neuroscientist Warren S. McCulloch entitled "A logical calculus of the ideas immanent in nervous activity" was regarded as a breakthrough in laying the first foundations of machine learning. It indicates the usage of mathematical principles to detail the science and psychology behind human decision-making. However, in 1950, Alan Turing introduced what computer scientists now know of as the "Turing Test" to determine whether a machine can be considered intelligent or unintelligent.