Recently, self-supervised learning methods based on masked latent prediction have proven to encode input data into powerful representations. However, during training, the learned latent space can be further transformed to extract higher-level information that could be more suited for downstream classification tasks. Therefore, we propose a new method: MAsked latenT Prediction And Classification (MATPAC), which is trained with two pretext tasks solved jointly. As in previous work, the first pretext task is a masked latent prediction task, ensuring a robust input representation in the latent space. The second one is unsupervised classification, which utilises the latent representations of the first pretext task to match probability distributions between a teacher and a student. We validate the MATPAC method by comparing it to other state-of-the-art proposals and conducting ablations studies. MATPAC reaches state-of-the-art self-supervised learning results on reference audio classification datasets such as OpenMIC, GTZAN, ESC-50 and US8K and outperforms comparable supervised methods results for musical auto-tagging on Magna-tag-a-tune.

The growing amount of data produced by simulations and observations of space physics processes encourages the use of methods rooted in Machine Learning for data analysis and physical discovery. We apply a clustering method based on Self-Organizing Maps (SOM) to fully kinetic simulations of plasmoid instability, with the aim of assessing its suitability as a reliable analysis tool for both simulated and observed data. We obtain clusters that map well, a posteriori, to our knowledge of the process: the clusters clearly identify the inflow region, the inner plasmoid region, the separatrices, and regions associated with plasmoid merging. SOM-specific analysis tools, such as feature maps and Unified Distance Matrix, provide one with valuable insights into both the physics at work and specific spatial regions of interest. The method appears as a promising option for the analysis of data, both from simulations and from observations, and could also potentially be used to trigger the switch to different simulation models or resolution in coupled codes for space simulations.

This paper presents an unsupervised learning scheme for categorizing 3D objects from their 2D projected images. The scheme exploits an auto-associative network's ability to encode each view of a single object into a representation that indicates its view direction. We propose two models that employ different classification mechanisms; the first model selects an auto-associative network whose recovered view best matches the input view, and the second model is based on a modular architecture whose additional network classifies the views by splitting the input space nonlinearly. We demonstrate the effectiveness of the proposed classification models through simulations using 3D wire-frame objects.

We present an unsupervised classification algorithm based on an ICA mixture model. The ICA mixture model assumes that the observed data can be categorized into several mutually exclusive data classes in which the components in each class are generated by a linear mixture of independent sources. The algorithm finds the independent sources, the mixing matrix for each class and also computes the class membership probability for each data point. This approach extends the Gaussian mixture model so that the classes can have non-Gaussian structure. We demonstrate that this method can learn efficient codes to represent images of natural scenes and text.

It has been my impression, that in the immense space of Artificial Intelligence (AI) concepts and tools, Generative Adversarial Networks (GANs) stand aside as an untamed beast. Everybody realizes how powerful and cool they are, few know how to train them, and even fewer can actually find any use for them for a practical task. I might be wrong, so feel free to correct me. Meanwhile, I would like to take another look at this wonderful machinery and investigate its possible use for classification and embedding. GANs were introduced in reference [1]. They consist of two parts -- a discriminator and a generator. A discriminator is a function that takes in an object and converts it into a number. Of course, depending on the complexity of the object, it might be a formidable task to turn it into a number. For that reason, we might employ a pretty sophisticated function for a discriminator, like, for instance, a deep layered Convolutional Neural Network (CNN).

Skilled AI workers are being urgently sought. Knowledge and some experience in artificial intelligence and machine learning are the job skills most in demand in 2021. That is confirmed in a survey by Hackerearth of 2,500 developer recruiters and hiring managers reported in a recent account in The Enterprisers Project. The AI field is expansive, with a wide range of skills represented. "This is an incredibly broad field, and not all jobs will require the same skills. As your organization competes for talent, don't let enthusiasm cloud your judgment," stated Rajan Sethuraman, CEO of LatentView Analytics, author of the piece.

This tutorial shows you how to perform unsupervised classification (e.g., KMeans clustering) in Earth Engine. The ee.Clusterer package handles unsupervised classification (or clustering) in Earth Engine. These algorithms are currently based on the algorithms with the same name in Weka. More details about each Clusterer are available in the reference docs in the Code Editor. Clusterers are used in the same manner as classifiers in Earth Engine.

Clustering is sometimes called "unsupervised classification", a term that I have mixed feelings on for reasons I will cover shortly, but it provides a good enough explanation of the problem to be worth covering. First, the problem is unsupervised -- we won't have a labeled dataset to guide our logic. Secondly we are looking to separate items into classes based on the predictors (technically they are not predictors they are "features" here because there is no response). The difference is that in supervised classification the class structure is known and labeled, whereas in clustering we are inventing the class structure from the feature values alone. In supervised classification we used the labels to single out one class and looked for predictors that had two qualities: 1) They had fairly common values for every example of that class and 2) they separated that class from others.

Understanding local currents in the North Atlantic region of the ocean is a key part of modelling heat transfer and global climate patterns. Satellites provide a surface signature of the temperature of the ocean with a high horizontal resolution while in situ autonomous probes supply high vertical resolution, but horizontally sparse, knowledge of the ocean interior thermal structure. The objective of this paper is to develop a methodology to combine these complementary ocean observing systems measurements to obtain a three-dimensional time series of ocean temperatures with high horizontal and vertical resolution. Within an observation-driven framework, we investigate the extent to which mesoscale ocean dynamics in the North Atlantic region may be decomposed into a mixture of dynamical modes, characterized by different local regressions between Sea Surface Temperature (SST), Sea Level Anomalies (SLA) and Vertical Temperature fields. Ultimately we propose a Latent-class regression method to improve prediction of vertical ocean temperature.

I want to classify a collection of documents, but I would also very much like it to be able to generate names for its categories on its own. So - clustering is a way to do unsupervised learning, but how would you expect a computer to be able to generate meaningful names for those clusters?