Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, verifying quality and safety becomes increasingly challenging. This paper explores how we can leverage AI to improve the quality of human oversight. We focus on an important safety problem that is already challenging for humans: fact-verification of AI outputs. We find that combining AI ratings and human ratings based on AI rater confidence is better than relying on either alone. Giving humans an AI fact-verification assistant further improves their accuracy, but the type of assistance matters. Displaying AI explanation, confidence, and labels leads to over-reliance, but just showing search results and evidence fosters more appropriate trust. These results have implications for Amplified Oversight -- the challenge of combining humans and AI to supervise AI systems even as they surpass human expert performance.

Efficiency is essential to support ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations. Our key insight is that, while DL programs typically execute sequentially, hybridizing imperative DL code resembles parallelizing sequential code in traditional systems. Inspired by this, we present an automated refactoring approach that assists developers in determining which otherwise eagerly-executed imperative DL functions could be effectively and efficiently executed as graphs. The approach features novel static imperative tensor and side-effect analyses for Python. Due to its inherent dynamism, analyzing Python may be unsound; however, the conservative approach leverages a speculative (keyword-based) analysis for resolving difficult cases that informs developers of any assumptions made. The approach is: (i) implemented as a plug-in to the PyDev Eclipse IDE that integrates the WALA Ariadne analysis framework and (ii) evaluated on nineteen DL projects consisting of 132 KLOC. The results show that 326 of 766 candidate functions (42.56%) were refactorable, and an average relative speedup of 2.16x on performance tests was observed with negligible differences in model accuracy. The results indicate that the approach is useful in optimizing imperative DL code to its full potential.

Time-series prediction is an active area of research across various fields, often challenged by the fluctuating influence of short-term and long-term factors. In this study, we introduce a feature engineering method that enhances the predictive performance of neural network models. Specifically, we leverage computational topology techniques to derive valuable topological features from input data, boosting the predictive accuracy of our models. Our focus is on predicting wave heights, utilizing models based on topological features within feedforward neural networks (FNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTM), and RNNs with gated recurrent units (GRU). For time-ahead predictions, the enhancements in $R^2$ score were significant for FNNs, RNNs, LSTM, and GRU models. Additionally, these models also showed significant reductions in maximum errors and mean squared errors.

Spiking neural networks (SNNs) have received widespread attention as an ultra-low energy computing paradigm. Recent studies have focused on improving the feature extraction capability of SNNs, but they suffer from inefficient inference and suboptimal performance. In this paper, we propose a simple yet effective temporal reversed training (TRT) method to optimize the spatio-temporal performance of SNNs and circumvent these problems. We perturb the input temporal data by temporal reversal, prompting the SNN to produce original-reversed consistent output logits and to learn perturbation-invariant representations. For static data without temporal dimension, we generalize this strategy by exploiting the inherent temporal property of spiking neurons for spike feature temporal reversal. In addition, we utilize the lightweight ``star operation" (element-wise multiplication) to hybridize the original and temporally reversed spike firing rates and expand the implicit dimensions, which serves as spatio-temporal regularization to further enhance the generalization of the SNN. Our method involves only an additional temporal reversal operation and element-wise multiplication during training, thus incurring negligible training overhead and not affecting the inference efficiency at all. Extensive experiments on static/neuromorphic object/action recognition, and 3D point cloud classification tasks demonstrate the effectiveness and generalizability of our method. In particular, with only two timesteps, our method achieves 74.77\% and 90.57\% accuracy on ImageNet and ModelNet40, respectively.

Class imbalance poses a major challenge in different classification tasks, which is a frequently occurring scenario in many real-world applications. Data resampling is considered to be the standard approach to address this issue. The goal of the technique is to balance the class distribution by generating new samples or eliminating samples from the data. A wide variety of sampling techniques have been proposed over the years to tackle this challenging problem. Sampling techniques can also be incorporated into the ensemble learning framework to obtain more generalized prediction performance. Balanced Random Forest (BRF) and SMOTE-Bagging are some of the popular ensemble approaches. In this study, we propose a modification to the BRF classifier to enhance the prediction performance. In the original algorithm, the Random Undersampling (RUS) technique was utilized to balance the bootstrap samples. However, randomly eliminating too many samples from the data leads to significant data loss, resulting in a major decline in performance. We propose to alleviate the scenario by incorporating a novel hybrid sampling approach to balance the uneven class distribution in each bootstrap sub-sample. Our proposed hybrid sampling technique, when incorporated into the framework of the Random Forest classifier, termed as iBRF: improved Balanced Random Forest classifier, achieves better prediction performance than other sampling techniques used in imbalanced classification tasks. Experiments were carried out on 44 imbalanced datasets on which the original BRF classifier produced an average MCC score of 47.03% and an F1 score of 49.09%. Our proposed algorithm outperformed the approach by producing a far better MCC score of 53.04% and an F1 score of 55%. The results obtained signify the superiority of the iBRF algorithm and its potential to be an effective sampling technique in imbalanced learning.

Particle Swarm Optimization (PSO) has emerged as a powerful metaheuristic global optimization approach over the past three decades. Its appeal lies in its ability to tackle complex multidimensional problems that defy conventional algorithms. However, PSO faces challenges, such as premature stagnation in single-objective scenarios and the need to strike a balance between exploration and exploitation. Hybridizing PSO by integrating its cooperative nature with established optimization techniques from diverse paradigms offers a promising solution. In this paper, we investigate various strategies for synergizing gradient-based optimizers with PSO. We introduce different hybridization principles and explore several approaches, including sequential decoupled hybridization, coupled hybridization, and adaptive hybridization. These strategies aim to enhance the efficiency and effectiveness of PSO, ultimately improving its ability to navigate intricate optimization landscapes. By combining the strengths of gradient-based methods with the inherent social dynamics of PSO, we seek to address the critical objectives of intelligent exploration and exploitation in complex optimization tasks. Our study delves into the comparative merits of these hybridization techniques and offers insights into their application across different problem domains.

In this paper, we are interested in the acceleration of numerical simulations. We focus on a hypersonic planetary reentry problem whose simulation involves coupling fluid dynamics and chemical reactions. Simulating chemical reactions takes most of the computational time but, on the other hand, cannot be avoided to obtain accurate predictions. We face a trade-off between cost-efficiency and accuracy: the simulation code has to be sufficiently efficient to be used in an operational context but accurate enough to predict the phenomenon faithfully. To tackle this trade-off, we design a hybrid simulation code coupling a traditional fluid dynamic solver with a neural network approximating the chemical reactions. We rely on their power in terms of accuracy and dimension reduction when applied in a big data context and on their efficiency stemming from their matrix-vector structure to achieve important acceleration factors ($\times 10$ to $\times 18.6$). This paper aims to explain how we design such cost-effective hybrid simulation codes in practice. Above all, we describe methodologies to ensure accuracy guarantees, allowing us to go beyond traditional surrogate modeling and to use these codes as references.

Musical Metacreation tries to obtain creative behaviors from computers algorithms composing music. In this paper I briefly analyze how this field evolved from algorithmic composition to be focused on the search for creativity, and I point out some issues in pursuing this goal. Finally, I argue that hybridization of algorithms can be a useful direction for research.

Abstract: DNA encoded libraries (DELs) are used for rapid large-scale screening of small molecules against a protein target. These combinatorial libraries are built through several cycles of chemistry and DNA ligation, producing large sets of DNA-tagged molecules. Training machine learning models on DEL data has been shown to be effective at predicting molecules of interest dissimilar from those in the original DEL. Machine learning chemical property prediction approaches rely on the assumption that the property of interest is linked to a single chemical structure. In the context of DNA-encoded libraries, this is equivalent to assuming that every chemical reaction fully yields the desired product.

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce DL code that is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, less error-prone imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. While hybrid approaches aim for the "best of both worlds," the challenges in applying them in the real world are largely unknown. We conduct a data-driven analysis of challenges -- and resultant bugs -- involved in writing reliable yet performant imperative DL code by studying 250 open-source projects, consisting of 19.7 MLOC, along with 470 and 446 manually examined code patches and bug reports, respectively. The results indicate that hybridization: (i) is prone to API misuse, (ii) can result in performance degradation -- the opposite of its intention, and (iii) has limited application due to execution mode incompatibility. We put forth several recommendations, best practices, and anti-patterns for effectively hybridizing imperative DL code, potentially benefiting DL practitioners, API designers, tool developers, and educators.