We propose a robust parameter estimation method for dynamical systems based on Statistical Learning techniques which aims to estimate a set of parameters that well fit the dynamics in order to obtain robust evidences about the qualitative behaviour of its trajectory. The method is quite general and flexible, since it dos not rely on any specific property of the dynamical system, and represents a mathematical formalisation of the procedure consisting of sampling and testing parameters, in which evolutions generated by candidate parameters are tested against observed data to assess goodness-of-fit. The Statistical Learning framework introduces a mathematically rigorous scheme to this general approach for parameter estimation, adding to the great field of parameter estimation in dynamical systems. The method is specially useful for estimating parameters in epidemiological compartmental models. We illustrate it in simulated and real data about COVID-19 spread in the US in order to assess qualitatively the peak of deaths by the disease.

While modern large-scale datasets often consist of heterogeneous subpopulations---for example, multiple demographic groups or multiple text corpora---the standard practice of minimizing average loss fails to guarantee uniformly low losses across all subpopulations. We propose a convex procedure that controls the worst-case performance over all subpopulations of a given size. Our procedure comes with finite-sample (nonparametric) convergence guarantees on the worst-off subpopulation. Empirically, we observe on lexical similarity, wine quality, and recidivism prediction tasks that our worst-case procedure learns models that do well against unseen subpopulations.

Scores based on Shapley values are currently widely used for providing explanations to classification results over machine learning models. A prime example of this corresponds to the influential SHAP-score, a version of the Shapley value in which the contribution of a set $S$ of features from a given entity $\mathbf{e}$ over a model $M$ is defined as the expected value in $M$ of the set of entities $\mathbf{e}'$ that coincide with $\mathbf{e}$ over all features in $S$. While in general computing Shapley values is a computationally intractable problem, it has recently been claimed that the SHAP-score can be computed in polynomial time over the class of decision trees. In this paper, we provide a proof of a stronger result over Boolean models: the SHAP-score can be computed in polynomial time over deterministic and decomposable Boolean circuits, also known as tractable probabilistic circuits. Such circuits encompass a wide range of Boolean circuits and binary decision diagrams classes, including binary decision trees and Ordered Binary Decision Diagrams (OBDDs). Moreover, we establish the computational limits of the notion of SHAP-score by showing that computing it over a class of Boolean models is always (polynomially) as hard as the model counting problem for this class (under some mild condition). This implies, for instance, that computing the SHAP-score for DNF propositional formulae is a #P-hard problem, and, thus, that determinism is essential for the circuits that we consider.

When a young girl came to New York University (NYU) Langone Health for a routine follow-up, tests seemed to show that the medulloblastoma for which she had been treated a few years earlier had returned. The girl's recurrent cancer was found in the same part of brain as before, and the biopsy seemed to confirm medulloblastoma. With this diagnosis, the girl would begin a specific course of radiotherapy and chemotherapy. But just as neuropathologist Matija Snuderl was about to sign off on the diagnosis and set her on that treatment path, he hesitated. The biopsy was slightly unusual, he thought, and he remembered a previous case in which what was thought to be medulloblastoma turned out to be something else. So, to help him make up his mind, Snuderl turned to a computer.

The most reliable predictor of a relationship's success is partners' belief that the other person is fully committed, a Western University-led international research team has found. Other important factors in a successful relationship include feeling close to, appreciated by and sexually satisfied with your partner, says the study – the first-ever systematic attempt at using machine-learning algorithms to predict people's relationship satisfaction. "Satisfaction with romantic relationships has important implications for health, wellbeing and work productivity," Western Psychology professor Samantha Joel said. "But research on predictors of relationship quality is often limited in scope and scale, and carried out separately in individual laboratories." The massive machine-learning study, conducted by Joel, Paul Eastwick from University of California, Davis, and 84 other scholars from around the world, delved into more than 11,000 couples and 43 distinct self-reported datasets on romantic couples.

The major Artificial Intelligence Chipsets producing areas include North America, Europe, Asia-Pacific, Middle-East, and Africa. Artificial Intelligence Chipsets industry states and outlook (2020-2027) is introduced in this part. Additionally, Artificial Intelligence Chipsets market dynamics stating the opportunities, market risk, and key driving forces are researched. Part 2: This part covers Artificial Intelligence Chipsets manufacturers profile based On their small business overview, product type, and program. Additionally, the sales volume, Artificial Intelligence Chipsets product cost, gross margin analysis, and Artificial Intelligence Chipsets market share of each participant is profiled in this report.

Autonomous driving is one of the most sought-after market in tech right now. Along other major changes in the automotive industry such as electric vehicles, connected cars, or ridesharing, autonomous driving is at the heart of what is considered to bethe second inflection point of mobility with a promise of a greener, safer, more convenient, and cheaper transportation. Indeed, just like we turned from horses to cars about a 100 years ago, mobility is slowly turning from mechanical transportation machines to supercomputers on wheels; creating a new land of opportunities for outsiders to come in and for balances of power to shift drastically in a trillion dollar automotive industry. "Autonomous driving is at the heart of what is considered the second inflection point of mobility." Since autonomous driving activities kicked off with the DARPA challenge in 2004, the ecosystem became a lot larger and fiercely competitive with OEMs and tier 1 suppliers now joined by internet companies, TELCOs, electronics manufacturers, and a large crowd of startups.

Data annotation using visual inspection (supervision) of each training sample can be laborious. Interactive solutions alleviate this by helping experts propagate labels from a few supervised samples to unlabeled ones based solely on the visual analysis of their feature space projection (with no further sample supervision). We present a semi-automatic data annotation approach based on suitable feature space projection and semi-supervised label estimation. We validate our method on the popular MNIST dataset and on images of human intestinal parasites with and without fecal impurities, a large and diverse dataset that makes classification very hard. We evaluate two approaches for semi-supervised learning from the latent and projection spaces, to choose the one that best reduces user annotation effort and also increases classification accuracy on unseen data. Our results demonstrate the added-value of visual analytics tools that combine complementary abilities of humans and machines for more effective machine learning.

Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few. In lockstep, regularization methods, which aim to prevent overfitting by penalizing the weight connections, or turning off some units, have been widely studied either. In this paper, we present a novel approach called MaxDropout, a regularizer for deep neural network models that works in a supervised fashion by removing (shutting off) the prominent neurons (i.e., most active) in each hidden layer. The model forces fewer activated units to learn more representative information, thus providing sparsity. Regarding the experiments, we show that it is possible to improve existing neural networks and provide better results in neural networks when Dropout is replaced by MaxDropout. The proposed method was evaluated in image classification, achieving comparable results to existing regularizers, such as Cutout and RandomErasing, also improving the accuracy of neural networks that uses Dropout by replacing the existing layer by MaxDropout.

Max-margin methods for binary classification such as the support vector machine (SVM) have been extended to the structured prediction setting under the name of max-margin Markov networks ($M^3N$), or more generally structural SVMs. Unfortunately, these methods are statistically inconsistent when the relationship between inputs and labels is far from deterministic. We overcome such limitations by defining the learning problem in terms of a "max-min" margin formulation, naming the resulting method max-min margin Markov networks ($M^4N$). We prove consistency and finite sample generalization bounds for $M^4N$ and provide an explicit algorithm to compute the estimator. The algorithm achieves a generalization error of $O(1/\sqrt{n})$ for a total cost of $O(n)$ projection-oracle calls (which have at most the same cost as the max-oracle from $M^3N$). Experiments on multi-class classification, ordinal regression, sequence prediction and ranking demonstrate the effectiveness of the proposed method.