We develop a simple framework to learn bio-inspired foraging policies using human data. We conduct an experiment where humans are virtually immersed in an open field foraging environment and are trained to collect the highest amount of rewards. A Markov Decision Process (MDP) framework is introduced to model the human decision dynamics. Then, Imitation Learning (IL) based on maximum likelihood estimation is used to train Neural Networks (NN) that map human decisions to observed states. The results show that passive imitation substantially underperforms humans. We further refine the human-inspired policies via Reinforcement Learning (RL) using the on-policy Proximal Policy Optimization (PPO) algorithm which shows better stability than other algorithms and can steadily improve the policies pretrained with IL. We show that the combination of IL and RL can match human results and that good performance strongly depends on combining the allocentric information with an egocentric representation of the environment.

Logic Mill is a scalable and openly accessible software system that identifies semantically similar documents within either one domain-specific corpus or multi-domain corpora. It uses advanced Natural Language Processing (NLP) techniques to generate numerical representations of documents. Currently it leverages a large pre-trained language model to generate these document representations. The system focuses on scientific publications and patent documents and contains more than 200 million documents. It is easily accessible via a simple Application Programming Interface (API) or via a web interface. Moreover, it is continuously being updated and can be extended to text corpora from other domains. We see this system as a general-purpose tool for future research applications in the social sciences and other domains.

Recent advances in upper limb prostheses have led to significant improvements in the number of movements provided by the robotic limb. However, the method for controlling multiple degrees of freedom via user-generated signals remains challenging. To address this issue, various machine learning controllers have been developed to better predict movement intent. As these controllers become more intelligent and take on more autonomy in the system, the traditional approach of representing the human-machine interface as a human controlling a tool becomes limiting. One possible approach to improve the understanding of these interfaces is to model them as collaborative, multi-agent systems through the lens of joint action. The field of joint action has been commonly applied to two human partners who are trying to work jointly together to achieve a task, such as singing or moving a table together, by effecting coordinated change in their shared environment. In this work, we compare different prosthesis controllers (proportional electromyography with sequential switching, pattern recognition, and adaptive switching) in terms of how they present the hallmarks of joint action. The results of the comparison lead to a new perspective for understanding how existing myoelectric systems relate to each other, along with recommendations for how to improve these systems by increasing the collaborative communication between each partner.

Many real-world applications of language models (LMs), such as code autocomplete and writing assistance, involve human-LM interaction, but the main LM benchmarks are non-interactive, where a system produces output without human intervention. To evaluate human-LM interaction, we develop a framework, Human-AI Language-based Interaction Evaluation (H-LINE), that expands non-interactive evaluation along three dimensions, capturing (i) the interactive process, not only the final output; (ii) the first-person subjective experience, not just a third-party assessment; and (iii) notions of preference beyond quality. We then design five tasks ranging from goal-oriented to open-ended to capture different forms of interaction. On four state-of-the-art LMs (three variants of OpenAI's GPT-3 and AI21's J1-Jumbo), we find that non-interactive performance does not always result in better human-LM interaction and that first-person and third-party metrics can diverge, suggesting the importance of examining the nuances of human-LM interaction.

In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. First, we present a realization pipeline showing the conversion of the models from Python libraries to the FPGA chip synthesis and implementation. Then, we review the main alternatives for the hardware implementation of nonlinear activation functions. The main results are divided into three parts: a performance comparison, an analysis of how activation functions are implemented, and a report on the complexity of the hardware. The performance in Q-factor is presented for the cases of bidirectional long-short-term memory coupled with convolutional NN (biLSTM + CNN) equalizer, CNN equalizer, and standard 1-StpS digital back-propagation (DBP) for the simulation and experiment propagation of a single channel dual-polarization (SC-DP) 16QAM at 34 GBd along 17x70km of LEAF. The biLSTM+CNN equalizer provides a similar result to DBP and a 1.7 dB Q-factor gain compared with the chromatic dispersion compensation baseline in the experimental dataset. After that, we assess the Q-factor and the impact of hardware utilization when approximating the activation functions of NN using Taylor series, piecewise linear, and look-up table (LUT) approximations. We also show how to mitigate the approximation errors with extra training and provide some insights into possible gradient problems in the LUT approximation. Finally, to evaluate the complexity of hardware implementation to achieve 400G throughput, fixed-point NN-based equalizers with approximated activation functions are developed and implemented in an FPGA.

Spatial nonstationarity, the location variance of features' statistical distributions, is ubiquitous in many natural settings. For example, in geological reservoirs rock matrix porosity varies vertically due to geomechanical compaction trends, in mineral deposits grades vary due to sedimentation and concentration processes, in hydrology rainfall varies due to the atmosphere and topography interactions, and in metallurgy crystalline structures vary due to differential cooling. Conventional geostatistical modeling workflows rely on the assumption of stationarity to be able to model spatial features for the geostatistical inference. Nevertheless, this is often not a realistic assumption when dealing with nonstationary spatial data and this has motivated a variety of nonstationary spatial modeling workflows such as trend and residual decomposition, cosimulation with secondary features, and spatial segmentation and independent modeling over stationary subdomains. The advent of deep learning technologies has enabled new workflows for modeling spatial relationships. However, there is a paucity of demonstrated best practice and general guidance on mitigation of spatial nonstationarity with deep learning in the geospatial context. We demonstrate the impact of two common types of geostatistical spatial nonstationarity on deep learning model prediction performance and propose the mitigation of such impacts using self-attention (vision transformer) models. We demonstrate the utility of vision transformers for the mitigation of nonstationarity with relative errors as low as 10%, exceeding the performance of alternative deep learning methods such as convolutional neural networks. We establish best practice by demonstrating the ability of self-attention networks for modeling large-scale spatial relationships in the presence of commonly observed geospatial nonstationarity.

As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adapt in dynamically-changing environments, becoming Lifelong Learning Machines. Continual/lifelong learning (LL) involves minimizing catastrophic forgetting of old tasks while maximizing a model's capability to learn new tasks. This paper addresses the challenging lifelong reinforcement learning (L2RL) setting. Pushing the state-of-the-art forward in L2RL and making L2RL useful for practical applications requires more than developing individual L2RL algorithms; it requires making progress at the systems-level, especially research into the non-trivial problem of how to integrate multiple L2RL algorithms into a common framework. In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system. As an instantiation of L2RLCF, we develop a standard API allowing easy integration of novel lifelong learning components. We describe a case study that demonstrates how multiple independently-developed LL components can be integrated into a single realized system. We also introduce an evaluation environment in order to measure the effect of combining various system components. Our evaluation environment employs different LL scenarios (sequences of tasks) consisting of Starcraft-2 minigames and allows for the fair, comprehensive, and quantitative comparison of different combinations of components within a challenging common evaluation environment.

Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.

This paper describes important considerations and challenges associated with online reinforcement-learning based waveform selection for target identification in frequency modulated continuous wave (FMCW) automotive radar systems. We present a novel learning approach based on satisficing Thompson sampling, which quickly identifies a waveform expected to yield satisfactory classification performance. We demonstrate through measurement-level simulations that effective waveform selection strategies can be quickly learned, even in cases where the radar must select from a large catalog of candidate waveforms. The radar learns to adaptively select a bandwidth for appropriate resolution and a slow-time unimodular code for interference mitigation in the scene of interest by optimizing an expected classification metric.

When should an online reinforcement learning-based frequency agile cognitive radar be expected to outperform a rule-based adaptive waveform selection strategy? We seek insight regarding this question by examining a dynamic spectrum access scenario, in which the radar wishes to transmit in the widest unoccupied bandwidth during each pulse repetition interval. Online learning is compared to a fixed rule-based sense-and-avoid strategy. We show that given a simple Markov channel model, the problem can be examined analytically for simple cases via stochastic dominance. Additionally, we show that for more realistic channel assumptions, learning-based approaches demonstrate greater ability to generalize. However, for short time-horizon problems that are well-specified, we find that machine learning approaches may perform poorly due to the inherent limitation of convergence time. We draw conclusions as to when learning-based approaches are expected to be beneficial and provide guidelines for future study.