Research connected to &quot;machine learning&quot;

Attacking and Defending Deep Reinforcement Learning Policies

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study the robustness of DRL policies to adversarial attacks from the perspective of robust optimization. Within the framework of robust optimization, optimal adversarial attacks are given by minimizing the expected return of the policy, and correspondingly a good defense mechanism should be realized by improving the worst-case performance of the policy. Considering that attackers generally have no access to the training environment, we propose a greedy attack algorithm, which tries to minimize the expected return of the policy without interacting with the environment, and a defense algorithm, which performs adversarial training in a max-min form. Experiments on Atari game environments show that our attack algorithm is more effective and leads to worse return of the policy than existing attack algorithms, and our defense algorithm yields policies more robust than existing defense methods to a range of adversarial attacks (including our proposed attack algorithm).

Optimal Recourse Summaries via Bi-Objective Decision Tree Learning

Actionable Recourse provides individuals with actions they can take to change an unfavorable classifier outcome. While useful at the instance level, it is ill-suited for global auditing and bias detection, since aggregating local actions is costly and often inconsistent. Recourse Summaries address this limitation by partitioning the population and assigning one shared action per subgroup, enabling comparison across subgroups. Designing summaries involves a fundamental trade-off between recourse effectiveness and recourse cost, which existing methods do not adequately address. We introduce Summaries of Optimal and Global Actionable Recourse (SOGAR), which formulates recourse summary learning as an optimal decision tree learning problem and finds the Pareto front -- the complete set of solutions where improving one objective necessarily worsens the other. SOGAR enables post-hoc selection of the desired trade-off without retraining. Using shallow axis-parallel decision trees and sparse leaf actions, SOGAR produces stable, low-cost, and effective recourse summaries that outperform existing approaches across effectiveness and cost metrics.

Lifelong Neural Predictive Coding: Learning Cumulatively Online without Forgetting

In lifelong learning systems based on artificial neural networks, one of the biggest obstacles is the inability to retain old knowledge as new information is encountered. This phenomenon is known as catastrophic forgetting. In this paper, we propose a new kind of connectionist architecture, the Sequential Neural Coding Network, that is robust to forgetting when learning from streams of data points and, unlike networks of today, does not learn via the popular back-propagation of errors. Grounded in the neurocognitive theory of predictive processing, our model adapts synapses in a biologically-plausible fashion while another neural system learns to direct and control this cortex-like structure, mimicking some of the task-executive control functionality of the basal ganglia. In our experiments, we demonstrate that our self-organizing system experiences significantly less forgetting compared to standard neural models, outperforming a swath of previously proposed methods, including rehearsal/data buffer-based methods, on both standard (SplitMNIST, Split Fashion MNIST, etc.) and custom benchmarks even though it is trained in a stream-like fashion. Our work offers evidence that emulating mechanisms in real neuronal systems, e.g., local learning, lateral competition, can yield new directions and possibilities for tackling the grand challenge of lifelong machine learning.

AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models

Recent healthcare foundation models have achieved strong predictive performance through large scale self supervised learning, yet their latent representations frequently entangle physiologic severity, intervention intensity, observational structure, and institutional workflow into shared embedding directions. While effective for downstream prediction, such representations remain semantically opaque and unstable under contextual shift. We introduce AURORA, Adaptive Uncertainty aware Representations through Orthogonalized Relational Alignment, a new framework for healthcare representation learning based on contextual latent geometry. Rather than optimizing a single unified embedding manifold, AURORA decomposes representations into orthogonal semantic subspaces corresponding to distinct contextual factors and learns relational consistency objectives within each subspace. This induces latent spaces that are both semantically disentangled and geometrically interpretable. Across multiple clinical prediction and retrieval tasks, AURORA consistently outperforms reconstruction, contrastive, and self distillation baselines while substantially improving contextual disentanglement, neighborhood purity, and robustness under institutional distribution shift. Our results suggest that latent geometry itself constitutes an important axis of healthcare foundation model design and that explicitly structuring representation space according to contextual semantics provides a complementary direction beyond conventional predictive compression objectives.

preprint2013arXiv

Cost-Sensitive Tree of Classifiers

Recently, machine learning algorithms have successfully entered large-scale real-world industrial applications (e.g. search engines and email spam filters). Here, the CPU cost during test time must be budgeted and accounted for. In this paper, we address the challenge of balancing the test-time cost and the classifier accuracy in a principled fashion. The test-time cost of a classifier is often dominated by the computation required for feature extraction-which can vary drastically across eatures. We decrease this extraction time by constructing a tree of classifiers, through which test inputs traverse along individual paths. Each path extracts different features and is optimized for a specific sub-partition of the input space. By only computing features for inputs that benefit from them the most, our cost sensitive tree of classifiers can match the high accuracies of the current state-of-the-art at a small fraction of the computational cost.

Improving the Robustness of Trading Strategy Backtesting with Boltzmann Machines and Generative Adversarial Networks

This article explores the use of machine learning models to build a market generator. The underlying idea is to simulate artificial multi-dimensional financial time series, whose statistical properties are the same as those observed in the financial markets. In particular, these synthetic data must preserve the probability distribution of asset returns, the stochastic dependence between the different assets and the autocorrelation across time. The article proposes then a new approach for estimating the probability distribution of backtest statistics. The final objective is to develop a framework for improving the risk management of quantitative investment strategies, in particular in the space of smart beta, factor investing and alternative risk premia.

Robust SDE-Based Variational Formulations for Solving Linear PDEs via Deep Learning

The combination of Monte Carlo methods and deep learning has recently led to efficient algorithms for solving partial differential equations (PDEs) in high dimensions. Related learning problems are often stated as variational formulations based on associated stochastic differential equations (SDEs), which allow the minimization of corresponding losses using gradient-based optimization methods. In respective numerical implementations it is therefore crucial to rely on adequate gradient estimators that exhibit low variance in order to reach convergence accurately and swiftly. In this article, we rigorously investigate corresponding numerical aspects that appear in the context of linear Kolmogorov PDEs. In particular, we systematically compare existing deep learning approaches and provide theoretical explanations for their performances. Subsequently, we suggest novel methods that can be shown to be more robust both theoretically and numerically, leading to substantial performance improvements.

Learning to combine primitive skills: A step towards versatile robotic manipulation

Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve complex tasks but require full state observability and are not adapted to dynamic scene changes. Recent learning methods can operate directly on visual inputs but typically require many demonstrations and/or task-specific reward engineering. In this work we aim to overcome previous limitations and propose a reinforcement learning (RL) approach to task planning that learns to combine primitive skills. First, compared to previous learning methods, our approach requires neither intermediate rewards nor complete task demonstrations during training. Second, we demonstrate the versatility of our vision-based task planning in challenging settings with temporary occlusions and dynamic scene changes. Third, we propose an efficient training of basic skills from few synthetic demonstrations by exploring recent CNN architectures and data augmentation. Notably, while all of our policies are learned on visual inputs in simulated environments, we demonstrate the successful transfer and high success rates when applying

Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control

Autonomous agents situated in real-world environments must be able to master large repertoires of skills. While a single short skill can be learned quickly, it would be impractical to learn every task independently. Instead, the agent should share knowledge across behaviors such that each task can be learned efficiently, and such that the resulting model can generalize to new tasks, especially ones that are compositions or subsets of tasks seen previously. A policy conditioned on a goal or demonstration has the potential to share knowledge between tasks if it sees enough diversity of inputs. However, these methods may not generalize to a more complex task at test time. We introduce compositional plan vectors (CPVs) to enable a policy to perform compositions of tasks without additional supervision. CPVs represent trajectories as the sum of the subtasks within them. We show that CPVs can be learned within a one-shot imitation learning framework without any additional supervision or information about task hierarchy, and enable a demonstration-conditioned policy to generalize to tasks that sequence twice as many skills as the tasks seen during training. Analogously to embeddings such a

preprint2016arXiv

Dynamic Privacy For Distributed Machine Learning Over Network

Privacy-preserving distributed machine learning becomes increasingly important due to the recent rapid growth of data. This paper focuses on a class of regularized empirical risk minimization (ERM) machine learning problems, and develops two methods to provide differential privacy to distributed learning algorithms over a network. We first decentralize the learning algorithm using the alternating direction method of multipliers (ADMM), and propose the methods of dual variable perturbation and primal variable perturbation to provide dynamic differential privacy. The two mechanisms lead to algorithms that can provide privacy guarantees under mild conditions of the convexity and differentiability of the loss function and the regularizer. We study the performance of the algorithms, and show that the dual variable perturbation outperforms its primal counterpart. To design an optimal privacy mechanisms, we analyze the fundamental tradeoff between privacy and accuracy, and provide guidelines to choose privacy parameters. Numerical experiments using customer information database are performed to corroborate the results on privacy and utility tradeoffs and design.

preprint2023arXiv

Solar Radiation Prediction in the UTEQ based on Machine Learning Models

This research explores the effectiveness of various Machine Learning (ML) models used to predicting solar radiation at the Central Campus of the State Technical University of Quevedo (UTEQ). The data was obtained from a pyranometer, strategically located in a high area of the campus. This instrument continuously recorded solar irradiance data since 2020, offering a comprehensive dataset encompassing various weather conditions and temporal variations. After a correlation analysis, temperature and the time of day were identified as the relevant meteorological variables that influenced the solar irradiance. Different machine learning algorithms such as Linear Regression, K-Nearest Neighbors, Decision Tree, and Gradient Boosting were compared using the evaluation metrics Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the Coefficient of Determination ($R^2$). The study revealed that Gradient Boosting Regressor exhibited superior performance, closely followed by the Random Forest Regressor. These models effectively captured the non-linear patterns in solar radiation, as evidenced by their low MSE and high $R^2$ values. With the aim of assess the performance of our ML models, we developed a web-based tool for the Solar Radiation Forecasting in the UTEQ available at http://https://solarradiationforecastinguteq.streamlit.app/. The results obtained demonstrate the effectiveness of our ML models in solar radiation prediction and contribute a practical utility in real-time solar radiation forecasting, aiding in efficient solar energy management.

Tackling benign nonconvexity with smoothing and stochastic gradients

Non-convex optimization problems are ubiquitous in machine learning, especially in Deep Learning. While such complex problems can often be successfully optimized in practice by using stochastic gradient descent (SGD), theoretical analysis cannot adequately explain this success. In particular, the standard analyses do not show global convergence of SGD on non-convex functions, and instead show convergence to stationary points (which can also be local minima or saddle points). We identify a broad class of nonconvex functions for which we can show that perturbed SGD (gradient descent perturbed by stochastic noise -- covering SGD as a special case) converges to a global minimum (or a neighborhood thereof), in contrast to gradient descent without noise that can get stuck in local minima far from a global solution. For example, on non-convex functions that are relatively close to a convex-like (strongly convex or PL) function we show that SGD can converge linearly to a global optimum.

preprint2016arXiv

Neural Autoregressive Distribution Estimation

We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation. They leverage the probability product rule and a weight sharing scheme inspired from restricted Boltzmann machines, to yield an estimator that is both tractable and has good generalization performance. We discuss how they achieve competitive performance in modeling both binary and real-valued observations. We also present how deep NADE models can be trained to be agnostic to the ordering of input dimensions used by the autoregressive product rule decomposition. Finally, we also show how to exploit the topological structure of pixels in images using a deep convolutional architecture for NADE.

preprint2013arXiv

A Nested HDP for Hierarchical Topic Models

We develop a nested hierarchical Dirichlet process (nHDP) for hierarchical topic modeling. The nHDP is a generalization of the nested Chinese restaurant process (nCRP) that allows each word to follow its own path to a topic node according to a document-specific distribution on a shared tree. This alleviates the rigid, single-path formulation of the nCRP, allowing a document to more easily express thematic borrowings as a random effect. We demonstrate our algorithm on 1.8 million documents from The New York Times.

Making Reinforcement Learning Work on Swimmer

The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy search methods such as genetic algorithms or evolution strategies. A lot of these papers report poor performance on SWIMMER from RL methods and much better performance from direct policy search methods. In this technical report we show that the low performance of RL methods on SWIMMER simply comes from the inadequate tuning of an important hyper-parameter, the discount factor. Furthermore we show that, by setting this hyper-parameter to a correct value, the issue can be easily fixed. Finally, for a set of often used RL algorithms, we provide a set of successful hyper-parameters obtained with the Stable Baselines3 library and its RL Zoo.

preprint2015arXiv

Modeling Compositionality with Multiplicative Recurrent Neural Networks

We present the multiplicative recurrent neural network as a general model for compositional meaning in language, and evaluate it on the task of fine-grained sentiment analysis. We establish a connection to the previously investigated matrix-space models for compositionality, and show they are special cases of the multiplicative recurrent net. Our experiments show that these models perform comparably or better than Elman-type additive recurrent neural networks and outperform matrix-space models on a standard fine-grained sentiment analysis corpus. Furthermore, they yield comparable results to structural deep models on the recently published Stanford Sentiment Treebank without the need for generating parse trees.

Decision Tree-Based Predictive Models for Academic Achievement Using College Students' Support Networks

In this study, we examine a set of primary data collected from 484 students enrolled in a large public university in the Mid-Atlantic United States region during the early stages of the COVID-19 pandemic. The data, called Ties data, included students' demographic and support network information. The support network data comprised of information that highlighted the type of support, (i.e. emotional or educational; routine or intense). Using this data set, models for predicting students' academic achievement, quantified by their self-reported GPA, were created using Chi-Square Automatic Interaction Detection (CHAID), a decision tree algorithm, and cforest, a random forest algorithm that uses conditional inference trees. We compare the methods' accuracy and variation in the set of important variables suggested by each algorithm. Each algorithm found different variables important for different student demographics with some overlap. For White students, different types of educational support were important in predicting academic achievement, while for non-White students, different types of emotional support were important in predicting academic achievement. The presence of differing types of routine support were important in predicting academic achievement for cisgender women, while differing types of intense support were important in predicting academic achievement for cisgender men.

preprint2014arXiv

Conic Multi-Task Classification

Traditionally, Multi-task Learning (MTL) models optimize the average of task-related objective functions, which is an intuitive approach and which we will be referring to as Average MTL. However, a more general framework, referred to as Conic MTL, can be formulated by considering conic combinations of the objective functions instead; in this framework, Average MTL arises as a special case, when all combination coefficients equal 1. Although the advantage of Conic MTL over Average MTL has been shown experimentally in previous works, no theoretical justification has been provided to date. In this paper, we derive a generalization bound for the Conic MTL method, and demonstrate that the tightest bound is not necessarily achieved, when all combination coefficients equal 1; hence, Average MTL may not always be the optimal choice, and it is important to consider Conic MTL. As a byproduct of the generalization bound, it also theoretically explains the good experimental results of previous relevant works. Finally, we propose a new Conic MTL model, whose conic combination coefficients minimize the generalization bound, instead of choosing them heuristically as has been done in previous meth

Weighted Fisher Discriminant Analysis in the Input and Feature Spaces

Fisher Discriminant Analysis (FDA) is a subspace learning method which minimizes and maximizes the intra- and inter-class scatters of data, respectively. Although, in FDA, all the pairs of classes are treated the same way, some classes are closer than the others. Weighted FDA assigns weights to the pairs of classes to address this shortcoming of FDA. In this paper, we propose a cosine-weighted FDA as well as an automatically weighted FDA in which weights are found automatically. We also propose a weighted FDA in the feature space to establish a weighted kernel FDA for both existing and newly proposed weights. Our experiments on the ORL face recognition dataset show the effectiveness of the proposed weighting schemes.

Frequent subgraph-based persistent homology for graph classification

Persistent homology (PH) has recently emerged as a powerful tool for extracting topological features. Integrating PH into machine learning and deep learning models enhances topology awareness and interpretability. However, most PH methods on graphs rely on a limited set of filtrations, such as degree-based or weight-based filtrations, which overlook richer features like recurring information across the dataset and thus restrict expressive power. In this work, we propose a novel graph filtration called Frequent Subgraph Filtration (FSF), which is derived from frequent subgraphs and produces stable and information-rich frequency-based persistent homology (FPH) features. We study the theoretical properties of FSF and provide both proofs and experimental validation. Beyond persistent homology itself, we introduce two approaches for graph classification: an FPH-based machine learning model (FPH-ML) and a hybrid framework that integrates FPH with graph neural networks (FPH-GNNs) to enhance topology-aware graph representation learning. Our frameworks bridge frequent subgraph mining and topological data analysis, offering a new perspective on topology-aware feature extraction. Experimental

preprint2010arXiv

Faithfulness in Chain Graphs: The Gaussian Case

This paper deals with chain graphs under the classic Lauritzen-Wermuth-Frydenberg interpretation. We prove that the regular Gaussian distributions that factorize with respect to a chain graph $G$ with $d$ parameters have positive Lebesgue measure with respect to $\mathbb{R}^d$, whereas those that factorize with respect to $G$ but are not faithful to it have zero Lebesgue measure with respect to $\mathbb{R}^d$. This means that, in the measure-theoretic sense described, almost all the regular Gaussian distributions that factorize with respect to $G$ are faithful to it.

preprint2016arXiv

Instant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping

Although deep neural networks (DNN) are able to scale with direct advances in computational power (e.g., memory and processing speed), they are not well suited to exploit the recent trends for parallel architectures. In particular, gradient descent is a sequential process and the resulting serial dependencies mean that DNN training cannot be parallelized effectively. Here, we show that a DNN may be replicated over a massive parallel architecture and used to provide a cumulative sampling of local solution space which results in rapid and robust learning. We introduce a complimentary convolutional bootstrapping approach that enhances performance of the parallel architecture further. Our parallelized convolutional bootstrapping DNN out-performs an identical fully-trained traditional DNN after only a single iteration of training.

preprint2010arXiv

Safe Feature Elimination in Sparse Supervised Learning

We investigate fast methods that allow to quickly eliminate variables (features) in supervised learning problems involving a convex loss function and a $l_1$-norm penalty, leading to a potentially substantial reduction in the number of variables prior to running the supervised learning algorithm. The methods are not heuristic: they only eliminate features that are {\em guaranteed} to be absent after solving the learning problem. Our framework applies to a large class of problems, including support vector machine classification, logistic regression and least-squares. The complexity of the feature elimination step is negligible compared to the typical computational effort involved in the sparse supervised learning problem: it grows linearly with the number of features times the number of examples, with much better count if data is sparse. We apply our method to data sets arising in text classification and observe a dramatic reduction of the dimensionality, hence in computational effort required to solve the learning problem, especially when very sparse classifiers are sought. Our method allows to immediately extend the scope of existing algorithms, allowing us to run them on data set

Improving Model Training via Self-learned Label Representations

Modern neural network architectures have shown remarkable success in several large-scale classification and prediction tasks. Part of the success of these architectures is their flexibility to transform the data from the raw input representations (e.g. pixels for vision tasks, or text for natural language processing tasks) to one-hot output encoding. While much of the work has focused on studying how the input gets transformed to the one-hot encoding, very little work has examined the effectiveness of these one-hot labels. In this work, we demonstrate that more sophisticated label representations are better for classification than the usual one-hot encoding. We propose Learning with Adaptive Labels (LwAL) algorithm, which simultaneously learns the label representation while training for the classification task. These learned labels can significantly cut down on the training time (usually by more than 50%) while often achieving better test accuracies. Our algorithm introduces negligible additional parameters and has a minimal computational overhead. Along with improved training times, our learned labels are semantically meaningful and can reveal hierarchical relationships that may be present in the data.

Why do tree-based models still outperform deep learning on tabular data?

While deep learning has enabled tremendous progress on text and image datasets, its superiority on tabular data is not clear. We contribute extensive benchmarks of standard and novel deep learning methods as well as tree-based models such as XGBoost and Random Forests, across a large number of datasets and hyperparameter combinations. We define a standard set of 45 datasets from varied domains with clear characteristics of tabular data and a benchmarking methodology accounting for both fitting models and finding good hyperparameters. Results show that tree-based models remain state-of-the-art on medium-sized data ($\sim$10K samples) even without accounting for their superior speed. To understand this gap, we conduct an empirical investigation into the differing inductive biases of tree-based models and Neural Networks (NNs). This leads to a series of challenges which should guide researchers aiming to build tabular-specific NNs: 1. be robust to uninformative features, 2. preserve the orientation of the data, and 3. be able to easily learn irregular functions. To stimulate research on tabular architectures, we contribute a standard benchmark and raw data for baselines: every point of a 20 000 compute hours hyperparameter search for each learner.

preprint2024arXiv

From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation

The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual predictions in form of attribution maps, thereby identifying where important features occur (but not providing information about what they represent), global explanation techniques visualize what concepts a model has generally learned to encode. Both types of methods thus only provide partial insights and leave the burden of interpreting the model's reasoning to the user. In this work we introduce the Concept Relevance Propagation (CRP) approach, which combines the local and global perspectives and thus allows answering both the "where" and "what" questions for individual predictions. We demonstrate the capability of our method in various settings, showcasing that CRP leads to more human interpretable explanations and provides deep insights into the model's representation and reasoning through concept atlases, concept composition analyses, and quantitative investigations of concept subspaces and their role in fine-grained decision making.

Convex Fairness Constrained Model Using Causal Effect Estimators

Recent years have seen much research on fairness in machine learning. Here, mean difference (MD) or demographic parity is one of the most popular measures of fairness. However, MD quantifies not only discrimination but also explanatory bias which is the difference of outcomes justified by explanatory features. In this paper, we devise novel models, called FairCEEs, which remove discrimination while keeping explanatory bias. The models are based on estimators of causal effect utilizing propensity score analysis. We prove that FairCEEs with the squared loss theoretically outperform a naive MD constraint model. We provide an efficient algorithm for solving FairCEEs in regression and binary classification tasks. In our experiment on synthetic and real-world data in these two tasks, FairCEEs outperformed an existing model that considers explanatory bias in specific cases.

preprint2013arXiv

On the Sample Complexity of Learning Bayesian Networks

In recent years there has been an increasing interest in learning Bayesian networks from data. One of the most effective methods for learning such networks is based on the minimum description length (MDL) principle. Previous work has shown that this learning procedure is asymptotically successful: with probability one, it will converge to the target distribution, given a sufficient number of samples. However, the rate of this convergence has been hitherto unknown. In this work we examine the sample complexity of MDL based learning procedures for Bayesian networks. We show that the number of samples needed to learn an epsilon-close approximation (in terms of entropy distance) with confidence delta is O((1/epsilon)^(4/3)log(1/epsilon)log(1/delta)loglog (1/delta)). This means that the sample complexity is a low-order polynomial in the error threshold and sub-linear in the confidence bound. We also discuss how the constants in this term depend on the complexity of the target distribution. Finally, we address questions of asymptotic minimality and propose a method for using the sample complexity results to speed up the learning process.

Simple Contrastive Graph Clustering

Contrastive learning has recently attracted plenty of attention in deep graph clustering for its promising performance. However, complicated data augmentations and time-consuming graph convolutional operation undermine the efficiency of these methods. To solve this problem, we propose a Simple Contrastive Graph Clustering (SCGC) algorithm to improve the existing methods from the perspectives of network architecture, data augmentation, and objective function. As to the architecture, our network includes two main parts, i.e., pre-processing and network backbone. A simple low-pass denoising operation conducts neighbor information aggregation as an independent pre-processing, and only two multilayer perceptrons (MLPs) are included as the backbone. For data augmentation, instead of introducing complex operations over graphs, we construct two augmented views of the same vertex by designing parameter un-shared siamese encoders and corrupting the node embeddings directly. Finally, as to the objective function, to further improve the clustering performance, a novel cross-view structural consistency objective function is designed to enhance the discriminative capability of the learned network. Extensive experimental results on seven benchmark datasets validate our proposed algorithm's effectiveness and superiority. Significantly, our algorithm outperforms the recent contrastive deep clustering competitors with at least seven times speedup on average.

Multi-Modal Trajectory Prediction of NBA Players

National Basketball Association (NBA) players are highly motivated and skilled experts that solve complex decision making problems at every time point during a game. As a step towards understanding how players make their decisions, we focus on their movement trajectories during games. We propose a method that captures the multi-modal behavior of players, where they might consider multiple trajectories and select the most advantageous one. The method is built on an LSTM-based architecture predicting multiple trajectories and their probabilities, trained by a multi-modal loss function that updates the best trajectories. Experiments on large, fine-grained NBA tracking data show that the proposed method outperforms the state-of-the-art. In addition, the results indicate that the approach generates more realistic trajectories and that it can learn individual playing styles of specific players.

preprint2021arXiv

Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word

With the rapid development of AI technology in recent years, there have been many studies with deep learning models in soft sensing area. However, the models have become more complex, yet, the data sets remain limited: researchers are fitting million-parameter models with hundreds of data samples, which is insufficient to exercise the effectiveness of their models and thus often fail to perform when implemented in industrial applications. To solve this long-lasting problem, we are providing large scale, high dimensional time series manufacturing sensor data from Seagate Technology to the public. We demonstrate the challenges and effectiveness of modeling industrial big data by a Soft Sensing Transformer model on these data sets. Transformer is used because, it has outperformed state-of-the-art techniques in Natural Language Processing, and since then has also performed well in the direct application to computer vision without introduction of image-specific inductive biases. We observe the similarity of a sentence structure to the sensor readings and process the multi-variable sensor readings in a time series in a similar manner of sentences in natural language. The high-dimensional time-series data is formatted into the same shape of embedded sentences and fed into the transformer model. The results show that transformer model outperforms the benchmark models in soft sensing field based on auto-encoder and long short-term memory (LSTM) models. To the best of our knowledge, we are the first team in academia or industry to benchmark the performance of original transformer model with large-scale numerical soft sensing data.