Interactions within human teams are highly complex, dynamic, and multidimensional. Understanding these dynamics can help improve team efficacy and predict future outcomes. However, machine learning approaches to model these dynamics require a significant amount of data to make meaningful predictions. This paper describes the design and implementation of the Complex Dynamics of Online Professional Squads (CDOPS) dataset, developed for exploring human team dynamics. CDOPS comprises a collection of over 1 million rounds of CounterStrike: Global Offensive (CS:GO) games played in professional tournaments under regulated Counter-Strike servers, providing a foundational dataset for exploring squad dynamics in the context of E-sports. We here provide the context of CS:GO followed by a description of the CDOPS dataset, how it was collected, and how we believe it may be best used.

Neural networks have emerged as powerful tools across various domains, exhibiting remarkable empirical performance that motivated their widespread adoption in safety-critical applications, which, in turn, necessitates rigorous formal verification techniques to ensure their reliability and robustness. Tight bound propagation plays a crucial role in the formal verification process by providing precise bounds that can be used to formulate and verify properties, such as safety, robustness, and fairness. While state-of-the-art tools use linear and convex approximations to compute upper/lower bounds for each neuron’s outputs, recent advances have shown that nonlinear approximations based on Bernstein polynomials lead to tighter bounds but suffer from scalability issues. To that end, this article introduces BERN-NN-IBF, a significant enhancement of the Bernstein-polynomial-based bound propagation algorithms. BERN-NN-IBF offers three main contributions: 1) a memory-efficient encoding of Bernstein polynomials to scale the bound propagation algorithms; 2) optimized tensor operations for the new polynomial encoding to maintain the integrity of the bounds while enhancing computational efficiency; and 3) tighter under-approximations of the ReLU activation function using quadratic polynomials tailored to minimize approximation errors. Through comprehensive testing, we demonstrate that BERN-NN-IBF achieves tighter bounds and higher computational efficiency compared to the original BERN-NN and state-of-the-art methods, including linear and convex programming used within the winner of the VNN-COMPETITION.

Constraints solvers play a significant role in the analysis, synthesis, and formal verification of complex cyber-physical systems. In this article, we study the problem of designing a scalable constraints solver for an important class of constraints named polynomial constraint inequalities (also known as nonlinear real arithmetic theory). In this article, we introduce a solver named PolyARBerNN that uses convex polynomials as abstractions for highly nonlinears polynomials. Such abstractions were previously shown to be powerful to prune the search space and restrict the usage of sound and complete solvers to small search spaces. Compared with the previous efforts on using convex abstractions, PolyARBerNN provides three main contributions namely (i) a neural network guided abstraction refinement procedure that helps selecting the right abstraction out of a set of pre-defined abstractions, (ii) a Bernstein polynomial-based search space pruning mechanism that can be used to compute tight estimates of the polynomial maximum and minimum values which can be used as an additional abstraction of the polynomials, and (iii) an optimizer that transforms polynomial objective functions into polynomial constraints (on the gradient of the objective function) whose solutions are guaranteed to be close to the global optima. These enhancements together allowed the PolyARBerNN solver to solve complex instances and scales more favorably compared to the state-of-the-art nonlinear real arithmetic solvers while maintaining the soundness and completeness of the resulting solver. In particular, our test benches show that PolyARBerNN achieved 100X speedup compared with Z3 8.9, Yices 2.6, and PVS (a solver that uses Bernstein expansion to solve multivariate polynomial constraints) on a variety of standard test benches. Finally, we implemented an optimizer called PolyAROpt that uses PolyARBerNN to solve constrained polynomial optimization problems. Numerical results show that PolyAROpt is able to solve high-dimensional and high order polynomial optimization problems with higher speed compared to the built-in optimizer in the Z3 8.9 solver.

In this paper, we present BERN-NN as an efficient tool to perform bound propagation of Neural Networks (NNs). Bound propagation is a critical step in wide range of NN model checkers and reachability analysis tools. Given a bounded input set, bound propagation algorithms aim to compute tight bounds on the output of the NN. So far, linear and convex optimizations have been used to perform bound propagation. Since neural networks are highly non-convex, state-of-the-art bound propagation techniques suffer from introducing large errors. To circumvent such drawback, BERN-NN approximates the bounds of each neuron using a class of polynomials called Bernstein polynomials. Bernstein polynomials enjoy several interesting properties that allow BERN-NN to obtain tighter bounds compared to those relying on linear and convex approximations. BERN-NN is efficiently parallelized on graphic processing units (GPUs). Extensive numerical results show that bounds obtained by BERN-NN are orders of magnitude tighter than those obtained by state-of-the-art verifiers such as linear programming and linear interval arithmetic. Moreoveer, BERN-NN is both faster and produces tighter outputs compared to convex programming approaches like alpha-CROWN.

In optical wireless communication (OWC) systems, channel estimation and detection of the transmitted symbols have been conventionally performed using analytical methods assuming that the optical channel follows a certain model, e.g., free-space model, input-dependent noise model, or Poisson model. In practical OWC systems, channels do not necessarily follow a specific model. Hence, it is difficult, if not impossible, to derive analytical models that provide optimal performance in realistic optical channels. Motivated by the success of neural networks in estimation and classification in various fields, we propose a neural network-based methodology for detection and estimation for OWC that does not rely on a channel model. Simulation results show that the proposed learning-based estimation and detection schemes achieve the optimal performance of the maximum likelihood detector under different channel state information assumptions.

Millimeter wave (mmWave) technology has been advocated as a promising infrastructure to provide reliable communications, both in indoor and outdoor environments. In this paper, we extend the application of mmWave to the uplink communication between smart meters (SMs) and a gateway. Such a communication is subject to interference from SMs belonging to adjacent networks and blockage caused by human bodies. Using a 3-D stochastic blockage model, we derive the outage probability. When human-body blockage is neglected, the high signal-to-noise-ratio (SNR) analysis shows a diversity gain of (mLM), where mLis the Nakagami-fading parameter of the line of sight (LOS) of the reference transmitter's channel, and M is the number of receive antennas at the gateway. Accounting for human-body blockage, the diversity gain reduces to (mNM), where mNis the Nakagami-fading parameter of the non LOS of the reference transmitter's channel. Our analysis shows that the probability that an SM is in LOS decays exponentially with the link length and the density of blockages. Although at high SNR blockage reduces the diversity gain, our numerical results show that blockage may decrease the outage probability at finite SNR.