Adaptive Tree Backup Algorithms for Temporal-Difference Reinforcement Learning

Q($\sigma$) is a recently proposed temporal-difference learning method that interpolates between learning from expected backups and sampled backups. It has been shown that intermediate values for the interpolation parameter $\sigma \in [0,1]$ perform better in practice, and therefore it is commonly believed that $\sigma$ functions as a bias-variance trade-off parameter to achieve these improvements. In our work, we disprove this notion, showing that the choice of $\sigma=0$ minimizes variance without increasing bias. This indicates that $\sigma$ must have some other effect on learning that is not fully understood. As an alternative, we hypothesize the existence of a new trade-off: larger $\sigma$-values help overcome poor initializations of the value function, at the expense of higher statistical variance. To automatically balance these considerations, we propose Adaptive Tree Backup (ATB) methods, whose weighted backups evolve as the agent gains experience. Our experiments demonstrate that adaptive strategies can be more effective than relying on fixed or time-annealed $\sigma$-values.

Logistic-ELM: A Novel Fault Diagnosis Method for Rolling Bearings

The fault diagnosis of rolling bearings is a critical technique to realize predictive maintenance for mechanical condition monitoring. In real industrial systems, the main challenges for the fault diagnosis of rolling bearings pertain to the accuracy and real-time requirements. Most existing methods focus on ensuring the accuracy, and the real-time requirement is often neglected. In this paper, considering both requirements, we propose a novel fast fault diagnosis method for rolling bearings, based on extreme learning machine (ELM) and logistic mapping, named logistic-ELM. First, we identify 14 kinds of time-domain features from the original vibration signals according to mechanical vibration principles and adopt the sequential forward selection (SFS) strategy to select optimal features from them to ensure the basic predictive accuracy and efficiency. Next, we propose the logistic-ELM for fast fault classification, where the biases in ELM are omitted and the random input weights are replaced by the chaotic logistic mapping sequence which involves a higher uncorrelation to obtain more accurate results with fewer hidden neurons. We conduct extensive experiments on the rolling bearing vibration signal dataset of the Case Western Reserve University (CWRU) Bearing Data Centre. The experimental results show that the proposed approach outperforms existing SOTA comparison methods in terms of the predictive accuracy, and the highest accuracy is 100% in seven separate sub data environments. The relevant code is publicly available at https://github.com/TAN-OpenLab/logistic-ELM.

Optimization of IoT-Enabled Physical Location Monitoring Using DT and VAR

This study shows an enhancement of IoT that gets sensor data and performs real-time face recognition to screen physical areas to find strange situations and send an alarm mail to the client to make remedial moves to avoid any potential misfortune in the environment. Sensor data is pushed onto the local system and GoDaddy Cloud whenever the camera detects a person to optimize the physical location monitoring system by reducing the bandwidth requirement and storage cost onto the cloud using edge computation. The study reveals that decision tree (DT) and random forest give reasonably similar macro average f1-scores to predict a person using sensor data. Experimental results show that DT is the most reliable predictive model for the cloud datasets of three different physical locations to predict a person using timestamp with an accuracy of 83.99%, 88.92%, and 80.97%. This study also explains multivariate time series prediction using vector auto regression that gives reasonably good root mean squared error to predict temperature, humidity, light-dependent resistor, and gas time series.

Visual Acuity Prediction on Real-Life Patient Data Using a Machine Learning Based Multistage System

In ophthalmology, intravitreal operative medication therapy (IVOM) is widespread treatment for diseases such as the age-related macular degeneration (AMD), the diabetic macular edema (DME), as well as the retinal vein occlusion (RVO). However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. Within our proposed multistage system, we classify the VA progression into the three groups of therapy "winners", "stabilizers", and "losers" (WSL scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98 %, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame. While achieving a prediction accuracy of up to 69 % (macro average F1-score) when considering all three WSL-based progression groups, this corresponds to an improvement by 11 % in comparison to our ophthalmic expertise (58 %).

NTS-NOTEARS: Learning Nonparametric Temporal DAGs With Time-Series Data and Prior Knowledge

We propose a score-based DAG structure learning method for time-series data that captures linear, nonlinear, lagged and instantaneous relations among variables while ensuring acyclicity throughout the entire graph. The proposed method extends nonparametric NOTEARS, a recent continuous optimization approach for learning nonparametric instantaneous DAGs. The proposed method is faster than constraint-based methods using nonlinear conditional independence tests. We also promote the use of optimization constraints to incorporate prior knowledge into the structure learning process. A broad set of experiments with simulated data demonstrates that the proposed method discovers better DAG structures than several recent comparison methods. We also evaluate the proposed method on complex real-world data acquired from NHL ice hockey games containing a mixture of continuous and discrete variables. The code is available at https://github.com/xiangyu-sun-789/NTS-NOTEARS/.

Flatten the Curve: Efficiently Training Low-Curvature Neural Networks

The highly non-linear nature of deep neural networks causes them to be susceptible to adversarial examples and have unstable gradients which hinders interpretability. However, existing methods to solve these issues, such as adversarial training, are expensive and often sacrifice predictive accuracy. In this work, we consider curvature, which is a mathematical quantity which encodes the degree of non-linearity. Using this, we demonstrate low-curvature neural networks (LCNNs) that obtain drastically lower curvature than standard models while exhibiting similar predictive performance, which leads to improved robustness and stable gradients, with only a marginally increased training time. To achieve this, we minimize a data-independent upper bound on the curvature of a neural network, which decomposes overall curvature in terms of curvatures and slopes of its constituent layers. To efficiently minimize this bound, we introduce two novel architectural components: first, a non-linearity called centered-softplus that is a stable variant of the softplus non-linearity, and second, a Lipschitz-constrained batch normalization layer. Our experiments show that LCNNs have lower curvature, more stable gradients and increased off-the-shelf adversarial robustness when compared to their standard high-curvature counterparts, all without affecting predictive performance. Our approach is easy to use and can be readily incorporated into existing neural network models.

Two ways towards combining Sequential Neural Network and Statistical Methods to Improve the Prediction of Time Series

Statistic modeling and data-driven learning are the two vital fields that attract many attentions. Statistic models intend to capture and interpret the relationships among variables, while data-based learning attempt to extract information directly from the data without pre-processing through complex models. Given the extensive studies in both fields, a subtle issue is how to properly integrate data based methods with existing knowledge or models. In this paper, based on the time series data, we propose two different directions to integrate the two, a decomposition-based method and a method exploiting the statistic extraction of data features. The first one decomposes the data into linear stable, nonlinear stable and unstable parts, where suitable statistical models are used for the linear stable and nonlinear stable parts while the appropriate machine learning tools are used for the unstable parts. The second one applies statistic models to extract statistics features of data and feed them as additional inputs into the machine learning platform for training. The most critical and challenging thing is how to determine and extract the valuable information from mathematical or statistical models to boost the performance of machine learning algorithms. We evaluate the proposal using time series data with varying degrees of stability. Performance results show that both methods can outperform existing schemes that use models and learning separately, and the improvements can be over 60%. Both our proposed methods are promising in bridging the gap between model-based and data-driven schemes and integrating the two to provide an overall higher learning performance.

Towards Using Promises for Multi-Agent Cooperation in Goal Reasoning

Reasoning and planning for mobile robots is a challenging problem, as the world evolves over time and thus the robot's goals may change. One technique to tackle this problem is goal reasoning, where the agent not only reasons about its actions, but also about which goals to pursue. While goal reasoning for single agents has been researched extensively, distributed, multi-agent goal reasoning comes with additional challenges, especially in a distributed setting. In such a context, some form of coordination is necessary to allow for cooperative behavior. Previous goal reasoning approaches share the agent's world model with the other agents, which already enables basic cooperation. However, the agent's goals, and thus its intentions, are typically not shared. In this paper, we present a method to tackle this limitation. Extending an existing goal reasoning framework, we propose enabling cooperative behavior between multiple agents through promises, where an agent may promise that certain facts will be true at some point in the future. Sharing these promises allows other agents to not only consider the current state of the world, but also the intentions of other agents when deciding on which goal to pursue next. We describe how promises can be incorporated into the goal life cycle, a commonly used goal refinement mechanism. We then show how promises can be used when planning for a particular goal by connecting them to timed initial literals (TILs) from PDDL planning. Finally, we evaluate our prototypical implementation in a simplified logistics scenario.

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

Few-shot in-context learning (ICL) enables pre-trained language models to perform a previously-unseen task without any gradient-based training by feeding a small number of training examples as part of the input. ICL incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made. Parameter-efficient fine-tuning (e.g. adapter modules, prompt tuning, sparse update methods, etc.) offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task. In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs. Along the way, we introduce a new parameter-efficient fine-tuning method called (IA)$^3$ that scales activations by learned vectors, attaining stronger performance while only introducing a relatively tiny amount of new parameters. We also propose a simple recipe based on the T0 model called T-Few that can be applied to new tasks without task-specific tuning or modifications. We validate the effectiveness of T-Few on completely unseen tasks by applying it to the RAFT benchmark, attaining super-human performance for the first time and outperforming the state-of-the-art by 6% absolute. All of the code used in our experiments is publicly available.

CS$^2$: A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Intervention

The destitution of image data and corresponding expert annotations limit the training capacities of AI diagnostic models and potentially inhibit their performance. To address such a problem of data and label scarcity, generative models have been developed to augment the training datasets. Previously proposed generative models usually require manually adjusted annotations (e.g., segmentation masks) or need pre-labeling. However, studies have found that these pre-labeling based methods can induce hallucinating artifacts, which might mislead the downstream clinical tasks, while manual adjustment could be onerous and subjective. To avoid manual adjustment and pre-labeling, we propose a novel controllable and simultaneous synthesizer (dubbed CS$^2$) in this study to generate both realistic images and corresponding annotations at the same time. Our CS$^2$ model is trained and validated using high resolution CT (HRCT) data collected from COVID-19 patients to realize an efficient infections segmentation with minimal human intervention. Our contributions include 1) a conditional image synthesis network that receives both style information from reference CT images and structural information from unsupervised segmentation masks, and 2) a corresponding segmentation mask synthesis network to automatically segment these synthesized images simultaneously. Our experimental studies on HRCT scans collected from COVID-19 patients demonstrate that our CS$^2$ model can lead to realistic synthesized datasets and promising segmentation results of COVID infections compared to the state-of-the-art nnUNet trained and fine-tuned in a fully supervised manner.