Abstract

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly able to learn from the sparse rewarding experience in the complex SMAC and RWARE domains. These findings highlight the importance of regularisation in the critic for stable learning.

Abstract

Music processing is a complex and intriguing phenomenon that has garnered extensive research interest in recent years. In this study, we investigated neural representations of music features by analyzing blood-oxygen-level-dependent (BOLD) signal fMRI activations of selected regions of interest during a continuous listening task. Additionally, we compared these activations to the hidden layer activations of a special class of deep neural networks (DNNs). Using representational similarity analysis, we found a strong correlation between low-level music feature encoding in the human brain regions of the Superior Temporal Gyrus (STG) and Heschl’s gyrus (HG) to the hidden layers of the DNN encoder. Our results suggest that self-supervised DNNs can serve as a reliable architecture to study the music processing domain, which is crucial considering the absence of naturalistic listening conditions in prior research Keywords: neural networks, representation similarity analysis, music cognition, music encoding, neuromusicology

Abstract

Bayesian Optimization (BO) is used to find the global optima of black box functions. In this work, we propose a practical BO method of function compositions where the form of the composition is known but the constituent functions are expensive to evaluate. By assuming an independent Gaussian process (GP) model for each of the constituent black-box function, we propose EI and UCB based BO algorithms and demonstrate their ability to outperform vanilla BO and the current state-of-art algorithms. We demonstrate a novel application of the proposed methods to dynamic pricing in revenue management when the underlying demand function is expensive to evaluate.

Abstract

Link forecasting in a temporal Knowledge Graph (tKG) in- volves predicting a future event from a given set of past events. Most previous studies suffered from reduced performance as they disregarded acyclic rules and enforced a tight constraint that all past events must exist in a strict temporal order. This paper proposes a novel explainable rule-based link forecasting framework by introducing two new concepts, namely ‘relaxed temporal cyclic and acyclic random walks’ and ‘link-star rules’. The former concept involves generating rules by performing cyclic and acyclic random walks on a tKG by taking into account the real-world phenomenon that the order of any two events may be ignored if their oc- currence time gap is within a threshold value. Link-star rules are a special class of acyclic rules generated based on the natural phenomenon that history repeats itself after a particular time. Link-star rules eliminate the problem of combinatorial rule explosion, thereby making our frame- work practicable. Experimental results demonstrate that our framework outperforms the state-of-the-art by a substantial margin. The evaluation measures hits@1 and mean reciprocal rank were improved by 45% and 23%, respectively. Keywords: Knowledge Graphs · Graph Analytics · Forecasting

Abstract

We consider a distributed multi-user secret sharing setting consisting of a dealer, n storage nodes and m secrets where each user demands a t-subset of m secrets. The user downloads shares from the storage nodes based on the designed access structure and reconstructs its secrets. Earlier work in this setting dealt with the case of t = 1; in this work, we generalize it to natural numbers. We identify a necessary condition on the access structures to ensure weak secrecy. We also make a connection between the access structures for this problem and t-disjunct matrices. We apply various t-disjunct matrix constructions in this setting and compare their performance in terms of the number of storage nodes and communication complexity. We also derive bounds on the optimal communication complexity of a distributed secret sharing protocol. Finally, we characterize the capacity region of the DMUSS problem when the access structure is specified

Abstract

The current study examines the role of constraints in well-defined problem-solving in ill-defined problem-solving. We chose variants of Raven’s advanced progressive matri- ces(APM) for well-defined problem-solving and creative rea- soning tasks (CRT) for ill-defined problem-solving. Using traditional APM, we created a novel version of APM with comparatively lesser constraints available to solve the puzzle, called creative APM(cAPM). The cAPM task was designed to induce divergent thinking along with convergent thinking. It is assumed that the difference in constraints changes the na- ture of the problem space in solving APM and cAPM and may differently affect the following creative reasoning task. We randomly assigned 50 participants to perform APM or cAPM, followed by the CRT, in a fixed order. We observed a sig- nificant effect of constraints available to solve well-defined problems on ill-defined problem-solving. The current result showed higher CRT scores when CRT preceded cAPM (Me- dian = 79.25) than APM (Median = 53.00). The result sug- gests that the flexibility in constraints to solve a well-defined problem induces more divergent thinking alongside convergent thinking and facilitates creative thinking required in ill-defined problem-solving.

Abstract

In this work, we describe the creation of our machine- learning-based solution for coma prognosis after cardiac arrest using longitudinal EEG and ECG recordings for the ”Predicting Neurological Recovery from Coma After Car- diac Arrest: The George B. Moody PhysioNet Challenge 2023”. Our team, “ComaToast”, had its best submission ranked 28 out of 36 teams selected worldwide, with a chal- lenge score of 0.381 on the official leaderboard for the hid- den test set. We use a combination of age and signal fea- tures from EEG and ECG recordings. Frequency domain features, specifically mean power spectral density from 4 different bands of frequencies (Delta, Theta, Alpha and Beta) and mean Burst Suppression Ratio, were extracted from pre-processed EEG recordings from the first and last available recording for a given patient. Features like mean and standard deviations were extracted along channels for ECG recordings. After imputing missing values, these fea- tures are fed to an XGBoost classifier for the final binary classification of the outcome prediction task. The features are fed to a random forest regressor to predict the CPC outcome for every patient. A solution like ours, which uses a simple model and training technique, may be more viable than deep-learning solutions in general use cases. In our final model, our approach achieved a 5-fold cross- validation score of 0.34 on the public train set.

Abstract

In this article, a novel adaptive controller is designed for Euler-Lagrangian systems under predefined time-varying state constraints. The proposed controller could achieve this objective without a priori knowledge of system parameters and, crucially, of state-dependent uncertainties. The closed-loop stability is verified using the Lyapunov method, while the overall efficacy of the proposed scheme is verified using a simulated robotic arm compared to the state of the art.

Abstract

The diverse excitabilities of cells often produce various spiking‑bursting oscillations that are found in the neural system. We establish the ability of a fractional‑order excitable neuron model with Caputo’s fractional derivative to analyze the effects of its dynamics on the spike train features observed in our results. The significance of this generalization relies on a theoretical framework of the model in which memory and hereditary properties are considered. Employing the fractional exponent, we first provide information about the variations in electrical activities. We deal with the 2D class I and class II excitable Morris‑Lecar (M‑L) neuron models that show the alternation of spiking and bursting features including MMOs & MMBOs of an uncoupled fractional‑order neuron. We then extend the study with the 3D slow‑fast M‑L model in the fractional domain. The considered approach establishes a way to describe various characteristics similarities between fractional‑order and classical integer‑order dynamics. Using the stability and bifurcation analysis, we discuss different parameter spaces where the quiescent state emerges in uncoupled neurons. We show the characteristics consistent with the analytical results. Next, the Erdös‑Rényi network of desynchronized mixed neurons (oscillatory and excitable) is constructed that is coupled through membrane voltage. It can generate complex firing activities where quiescent neurons start to fire. Furthermore, we have shown that increasing coupling can create cluster synchronization, and eventually it can enable the network to fire in unison. Based on cluster synchronization, we develop a reduced‑order model which can capture the activities of the entire network. Our results reveal that the effect of fractional‑order depends on the synaptic connectivity and the memory trace of the system. Additionally, the dynamics captures spike frequency adaptation and spike latency that occur over multiple timescales as the effects of fractional derivative, which has been observed in neural computation.

Abstract

Peripheral nerve blocks are crucial to treatment of post-surgical pain and are associated with reduction in perioperative opioid use and hospital stay. Accurate interpretation of sono-anatomy is critical for the success of ultrasound (US) guided peripheral nerve blocks and can be challenging to the new operators. This prospective study enrolled 227 subjects who were systematically scanned for supraclavicular and interscalene brachial plexus in various settings using three different US machines to create a dataset of 227 unique videos. In total, 41,000 video frames were annotated by experienced anaesthesiologists using partial automation with object tracking and active contour algorithms. Four baseline neural network models were trained on the dataset and their performance was evaluated for object detection and segmentation tasks. Generalizability of the best suited model was then tested on the datasets constructed from separate US scanners with and without fine-tuning. The results demonstrate that