With the rapid development of classical and quantum machine learning, a large number of machine learning frameworks have been proposed. However, existing machine learning frameworks usually only focus on classical or quantum, rather than both. Therefore, based on VQNet 1.0, we further propose VQNet 2.0, a new generation of unified classical and quantum machine learning framework that supports hybrid optimization. The core library of the framework is implemented in C++, and the user level is implemented in Python, and it supports deployment on quantum and classical hardware. In this article, we analyze the development trend of the new generation machine learning framework and introduce the design principles of VQNet 2.0 in detail: unity, practicality, efficiency, and compatibility, as well as full particulars of implementation. We illustrate the functions of VQNet 2.0 through several basic applications, including classical convolutional neural networks, quantum autoencoders, hybrid classical-quantum networks, etc. After that, through extensive experiments, we demonstrate that the operation speed of VQNet 2.0 is higher than the comparison method. Finally, through extensive experiments, we demonstrate that VQNet 2.0 can deploy on different hardware platforms, the overall calculation speed is faster than the comparison method. It also can be mixed and optimized with quantum circuits composed of multiple quantum computing libraries.
According to the rapid development of drone technologies, drones are widely used in many applications including military domains. In this paper, a novel situation-aware DRL- based autonomous nonlinear drone mobility control algorithm in cyber-physical loitering munition applications. On the battlefield, the design of DRL-based autonomous control algorithm is not straightforward because real-world data gathering is generally not available. Therefore, the approach in this paper is that cyber-physical virtual environment is constructed with Unity environment. Based on the virtual cyber-physical battlefield scenarios, a DRL-based automated nonlinear drone mobility control algorithm can be designed, evaluated, and visualized. Moreover, many obstacles exist which is harmful for linear trajectory control in real-world battlefield scenarios. Thus, our proposed autonomous nonlinear drone mobility control algorithm utilizes situation-aware components those are implemented with a Raycast function in Unity virtual scenarios. Based on the gathered situation-aware information, the drone can autonomously and nonlinearly adjust its trajectory during flight. Therefore, this approach is obviously beneficial for avoiding obstacles in obstacle-deployed battlefields. Our visualization-based performance evaluation shows that the proposed algorithm is superior from the other linear mobility control algorithms.
In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent has access to full information about the environment. We remove this assumption by developing an algorithm for IRL in partially observable Markov decision processes (POMDPs). We address two limitations of existing IRL techniques. First, they require an excessive amount of data due to the information asymmetry between the expert and the learner. Second, most of these IRL techniques require solving the computationally intractable forward problem -- computing an optimal policy given a reward function -- in POMDPs. The developed algorithm reduces the information asymmetry while increasing the data efficiency by incorporating task specifications expressed in temporal logic into IRL. Such specifications may be interpreted as side information available to the learner a priori in addition to the demonstrations. Further, the algorithm avoids a common source of algorithmic complexity by building on causal entropy as the measure of the likelihood of the demonstrations as opposed to entropy. Nevertheless, the resulting problem is nonconvex due to the so-called forward problem. We solve the intrinsic nonconvexity of the forward problem in a scalable manner through a sequential linear programming scheme that guarantees to converge to a locally optimal policy. In a series of examples, including experiments in a high-fidelity Unity simulator, we demonstrate that even with a limited amount of data and POMDPs with tens of thousands of states, our algorithm learns reward functions and policies that satisfy the task while inducing similar behavior to the expert by leveraging the provided side information.
This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no counterpart has been recognized by attention-based studies. This work rethinks lightweight infrastructure from efficient IRB and effective components of Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMB) for lightweight model design. Following simple but effective design criterion, we deduce a modern Inverted Residual Mobile Block (iRMB) and build a ResNet-like Efficient MOdel (EMO) with only iRMB for down-stream tasks. Extensive experiments on ImageNet-1K, COCO2017, and ADE20K benchmarks demonstrate the superiority of our EMO over state-of-the-art methods, e.g., EMO-1M/2M/5M achieve 71.5, 75.1, and 78.4 Top-1 that surpass equal-order CNN-/Attention-based models, while trading-off the parameter, efficiency, and accuracy well: running 2.8-4.0x faster than EdgeNeXt on iPhone14.
Ithaca is a Fuzzy Logic (FL) plugin for developing artificial intelligence systems within the Unity game engine. Its goal is to provide an intuitive and natural way to build advanced artificial intelligence systems, making the implementation of such a system faster and more affordable. The software is made up by a C\# framework and an Application Programming Interface (API) for writing inference systems, as well as a set of tools for graphic development and debugging. Additionally, a Fuzzy Control Language (FCL) parser is provided in order to import systems previously defined using this standard.
Survey questions often ask respondents to select from ordered scales where the meanings of the categories are subjective, leaving each individual free to apply their own definitions in answering. This paper studies the use of these responses as an outcome variable in causal inference, accounting for variation in interpretation of the categories across individuals. I find that when a continuous treatment variable is statistically independent of both i) potential outcomes; and ii) heterogeneity in reporting styles, a nonparametric regression of response category number on that treatment variable recovers a quantity proportional to an average causal effect among individuals who are on the margin between successive response categories. The magnitude of a given regression coefficient is not meaningful on its own, but the ratio of local regression derivatives with respect to two such treatment variables identifies the relative magnitudes of convex averages of their effects. These results can be seen as limiting cases of analogous results for binary treatment variables, though comparisons of magnitude involving discrete treatments are not as readily interpretable outside of the limit. I obtain a partial identification result for comparisons involving discrete treatments under further assumptions. An empirical application illustrates the results by revisiting the effects of income comparisons on subjective well-being, without assuming cardinality or interpersonal comparability of responses.
Direct speech-to-speech translation (S2ST), in which all components can be optimized jointly, is advantageous over cascaded approaches to achieve fast inference with a simplified pipeline. We present a novel two-pass direct S2ST architecture, UnitY, which first generates textual representations and predicts discrete acoustic units subsequently. We enhance the model performance by subword prediction in the first-pass decoder, advanced two-pass decoder architecture design and search strategy, and better training regularization. To leverage large amounts of unlabeled text data, we pre-train the first-pass text decoder based on the self-supervised denoising auto-encoding task. Experimental evaluations on benchmark datasets at various data scales demonstrate that UnitY outperforms a single-pass speech-to-unit translation model by 2.5-4.2 ASR-BLEU with 2.83x decoding speed-up. We show that the proposed methods boost the performance even when predicting spectrogram in the second pass. However, predicting discrete units achieves 2.51x decoding speed-up compared to that case.
To train deep learning models, which often outperform traditional approaches, large datasets of a specified medium, e.g., images, are used in numerous areas. However, for light field-specific machine learning tasks, there is a lack of such available datasets. Therefore, we create our own light field datasets, which have great potential for a variety of applications due to the abundance of information in light fields compared to singular images. Using the Unity and C# frameworks, we develop a novel approach for generating large, scalable, and reproducible light field datasets based on customizable hardware configurations to accelerate light field deep learning research.
This technical report details VEX Robotics team BLRSAI's development of a fully autonomous robot for VEX Robotics' Tipping Point AI Competition. We identify and develop three separate critical components. This includes a Unity simulation and reinforcement learning model training pipeline, a malleable computer vision pipeline, and a data transfer pipeline to offload large computations from the VEX V5 Brain/micro-controller to an external computer. We give the community access to all of these components in hopes they can reuse and improve upon them in the future, and that it'll spark new ideas for autonomy as well as the necessary infrastructure and programs for AI in educational robotics.
The use of computer vision for product and assembly quality control is becoming ubiquitous in the manufacturing industry. Lately, it is apparent that machine learning based solutions are outperforming classical computer vision algorithms in terms of performance and robustness. However, a main drawback is that they require sufficiently large and labeled training datasets, which are often not available or too tedious and too time consuming to acquire. This is especially true for low-volume and high-variance manufacturing. Fortunately, in this industry, CAD models of the manufactured or assembled products are available. This paper introduces CAD2Render, a GPU-accelerated synthetic data generator based on the Unity High Definition Render Pipeline (HDRP). CAD2Render is designed to add variations in a modular fashion, making it possible for high customizable data generation, tailored to the needs of the industrial use case at hand. Although CAD2Render is specifically designed for manufacturing use cases, it can be used for other domains as well. We validate CAD2Render by demonstrating state of the art performance in two industrial relevant setups. We demonstrate that the data generated by our approach can be used to train object detection and pose estimation models with a high enough accuracy to direct a robot. The code for CAD2Render is available at https://github.com/EDM-Research/CAD2Render.
Distribution grids are challenged by rapid voltage fluctuations induced by variable power injections from distributed energy resources (DERs). To regulate voltage, the IEEE Standard 1547 recommends each DER inject reactive power according to piecewise-affine Volt/VAR control rules. Although the standard suggests a default shape, the rule can be customized per bus. This task of optimal rule design (ORD) is challenging as Volt/VAR rules introduce nonlinear dynamics, and lurk trade-offs between stability and steady-state voltage profiles. ORD is formulated as a mixed-integer nonlinear program (MINLP), but scales unfavorably with the problem size. Towards a more efficient solution, we reformulate ORD as a deep learning problem. The idea is to design a DNN that emulates Volt/VAR dynamics. The DNN takes grid scenarios as inputs, rule parameters as weights, and outputs equilibrium voltages. Optimal rule parameters can be found by training the DNN so its output approaches unity for various scenarios. The DNN is only used to optimize rules and is never employed in the field. While dealing with ORD, we also review and expand on stability conditions and convergence rates for Volt/VAR dynamics on single- and multi-phase feeders. Tests showcase the merit of DNN-based ORD by benchmarking it against its MINLP counterpart.
In human-robot collaboration domains, augmented reality (AR) technologies have enabled people to visualize the state of robots. Current AR-based visualization policies are designed manually, which requires a lot of human efforts and domain knowledge. When too little information is visualized, human users find the AR interface not useful; when too much information is visualized, they find it difficult to process the visualized information. In this paper, we develop a framework, called VARIL, that enables AR agents to learn visualization policies (what to visualize, when, and how) from demonstrations. We created a Unity-based platform for simulating warehouse environments where human-robot teammates collaborate on delivery tasks. We have collected a dataset that includes demonstrations of visualizing robots' current and planned behaviors. Results from experiments with real human participants show that, compared with competitive baselines from the literature, our learned visualization strategies significantly increase the efficiency of human-robot teams, while reducing the distraction level of human users. VARIL has been demonstrated in a built-in-lab mock warehouse.
Hand, the bearer of human productivity and intelligence, is receiving much attention due to the recent fever of digital twins. Among different hand morphable models, MANO has been widely used in vision and graphics community. However, MANO disregards textures and accessories, which largely limits its power to synthesize photorealistic hand data. In this paper, we extend MANO with Diverse Accessories and Rich Textures, namely DART. DART is composed of 50 daily 3D accessories which varies in appearance and shape, and 325 hand-crafted 2D texture maps covers different kinds of blemishes or make-ups. Unity GUI is also provided to generate synthetic hand data with user-defined settings, e.g., pose, camera, background, lighting, textures, and accessories. Finally, we release DARTset, which contains large-scale (800K), high-fidelity synthetic hand images, paired with perfect-aligned 3D labels. Experiments demonstrate its superiority in diversity. As a complement to existing hand datasets, DARTset boosts the generalization in both hand pose estimation and mesh recovery tasks. Raw ingredients (textures, accessories), Unity GUI, source code and DARTset are publicly available at dart2022.github.io
A notion of disturbance propagation stability is defined for dynamical network processes, in terms of decrescence of an input-output energy metric along cutsets away from the disturbance source. A characterization of the disturbance propagation notion is developed for a canonical model for synchronization of linearly-coupled homogeneous subsystems. Specifically, propagation stability is equivalenced with the frequency response of a certain local closed-loop model, which is defined from the subsystem model and local network connections, being sub-unity gain. For the case where the subsystem is single-input single-output (SISO), a further simplification in terms of the subsystem's open loop Nyquist plot is obtained. An extension of the disturbance propagation stability concept toward imperviousness of subnetworks to disturbances is briefly developed, and an example focused on networks with planar subsystems is considered.
This paper considers highly persistent time series that are subject to nonlinearities in the form of censoring or an occasionally binding constraint, such as are regularly encountered in macroeconomics. A tractable candidate model for such series is the dynamic Tobit with a root local to unity. We show that this model generates a process that converges weakly to a non-standard limiting process, that is constrained (regulated) to be positive. Surprisingly, despite the presence of censoring, the OLS estimators of the model parameters are consistent. We show that this allows OLS-based inferences to be drawn on the overall persistence of the process (as measured by the sum of the autoregressive coefficients), and for the null of a unit root to be tested in the presence of censoring. Our simulations illustrate that the conventional ADF test substantially over-rejects when the data is generated by a dynamic Tobit with a unit root, whereas our proposed test is correctly sized. We provide an application of our methods to testing for a unit root in the Swiss franc / euro exchange rate, during a period when this was subject to an occasionally binding lower bound.
We explore the probabilistic partition of unity network (PPOU-Net) model in the context of high-dimensional regression problems and propose a general framework focusing on adaptive dimensionality reduction. With the proposed framework, the target function is approximated by a mixture of experts model on a low-dimensional manifold, where each cluster is associated with a local fixed-degree polynomial. We present a training strategy that leverages the expectation maximization (EM) algorithm. During the training, we alternate between (i) applying gradient descent to update the DNN coefficients; and (ii) using closed-form formulae derived from the EM algorithm to update the mixture of experts model parameters. Under the probabilistic formulation, step (ii) admits the form of embarrassingly parallelizable weighted least-squares solves. The PPOU-Nets consistently outperform the baseline fully-connected neural networks of comparable sizes in numerical experiments of various data dimensions. We also explore the proposed model in applications of quantum computing, where the PPOU-Nets act as surrogate models for cost landscapes associated with variational quantum circuits.
In this study, we propose parameter-varying neural ordinary differential equations (NODEs) where the evolution of model parameters is represented by partition-of-unity networks (POUNets), a mixture of experts architecture. The proposed variant of NODEs, synthesized with POUNets, learn a meshfree partition of space and represent the evolution of ODE parameters using sets of polynomials associated to each partition. We demonstrate the effectiveness of the proposed method for three important tasks: data-driven dynamics modeling of (1) hybrid systems, (2) switching linear dynamical systems, and (3) latent dynamics for dynamical systems with varying external forcing.
The availability of real data from areas with high privacy requirements, such as the medical intervention space, is low and the acquisition legally complex. Therefore, this work presents a way to create a synthetic dataset for the medical context, using medical clothing as an example. The goal is to close the reality gap between the synthetic and real data. For this purpose, methods of 3D-scanned clothing and designed clothing are compared in a Domain-Randomization and Structured-Domain-Randomization scenario using an Unreal-Engine plugin or Unity. Additionally a Mixed-Reality dataset in front of a greenscreen and a target domain dataset were used. Our experiments show, that Structured-Domain-Randomization of designed clothing together with Mixed-Reality data provide a baseline achieving 72.0% mAP on a test dataset of the clinical target domain. When additionally using 15% of available target domain train data, the gap towards 100% (660 images) target domain train data could be nearly closed 80.05% mAP (81.95% mAP). Finally we show that when additionally using 100% target domain train data the accuracy could be increased to 83.35% mAP.
We consider the problem of max-min fairness for uplink cell-free massive multiple-input multiple-output (MIMO) subject to per-user power constraints. The standard framework for solving the considered problem is to separately solve two subproblems: the receiver filter coefficient design and the power control problem. While the former has a closed-form solution, the latter has been solved using either second-order methods of high computational complexity or a first-order method that provides an approximate solution. To deal with these drawbacks of the existing methods, we propose a mirror prox based method for the power control problem by equivalently reformulating it as a convex-concave problem and applying the mirror prox algorithm to find a saddle point. The simulation results establish the optimality of the proposed solution and demonstrate that it is more efficient than the known methods. We also conclude that for large-scale cell-free massive MIMO, joint optimization of linear receive combining and power control provides significantly better user fairness than the power control only scheme in which receiver coefficients are fixed to unity.
The global financial crisis and Covid recession have renewed discussion concerning trend-cycle discovery in macroeconomic data, and boosting has recently upgraded the popular HP filter to a modern machine learning device suited to data-rich and rapid computational environments. This paper extends boosting's trend determination capability to higher order integrated processes and time series with roots that are local to unity. The theory is established by understanding the asymptotic effect of boosting on a simple exponential function. Given a universe of time series in FRED databases that exhibit various dynamic patterns, boosting timely captures downturns at crises and recoveries that follow.