Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about the very nature of explanation in neuroscience. Are we simply replacing one complex system (a biological circuit) with another (a deep network), without understanding either? Moreover, beyond neural representations, are the deep network's computational mechanisms for generating neural responses the same as those in the brain? Without a systematic approach to extracting and understanding computational mechanisms from deep neural network models, it can be difficult both to assess the degree of utility of deep learning approaches in neuroscience, and to extract experimentally testable hypotheses from deep networks. We develop such a systematic approach by combining dimensionality reduction and modern attribution methods for determining the relative importance of interneurons for specific visual computations. We apply this approach to deep network models of the retina, revealing a conceptual understanding of how the retina acts as a predictive feature extractor that signals deviations from expectations for diverse spatiotemporal stimuli. For each stimulus, our extracted computational mechanisms are consistent with prior scientific literature, and in one case yields a new mechanistic hypothesis. Thus overall, this work not only yields insights into the computational mechanisms underlying the striking predictive capabilities of the retina, but also places the framework of deep networks as neuroscientific models on firmer theoretical foundations, by providing a new roadmap to go beyond comparing neural representations to extracting and understand computational mechanisms.

We thank the reviewers for their constructive feedback. We thank R2 and R3 for raising that our paper lacks theoretical analysis. LU activation significantly improves GNN performance. We will add these new discussions to the revised paper. We thank reviewers for suggesting other design dimensions to explore.

Explainable AI (XAI) is a rapidly growing domain with a myriad of proposed methods as well as metrics aiming to evaluate their efficacy. However, current studies are often of limited scope, examining only a handful of XAI methods and ignoring underlying design parameters for performance, such as the model architecture or the nature of input data. Moreover, they often rely on one or a few metrics and neglect thorough validation, increasing the risk of selection bias and ignoring discrepancies among metrics. These shortcomings leave practitioners confused about which method to choose for their problem. In response, we introduce LATEC, a large-scale benchmark that critically evaluates 17 prominent XAI methods using 20 distinct metrics.

Large language models (LLMs) demonstrate strong language generation capabilities but often struggle with structured reasoning, leading to inconsistent or suboptimal problem-solving. To mitigate this limitation, Guilford's Structure of Intellect (SOI) model - a foundational framework from intelligence theory - is leveraged as the basis for cognitive prompt engineering. The SOI model categorizes cognitive operations such as pattern recognition, memory retrieval, and evaluation, offering a systematic approach to enhancing LLM reasoning and decision-making. This position paper presents a novel cognitive prompting approach for enforcing SOI-inspired reasoning for improving clarity, coherence, and adaptability in model responses.

Software testing ensures the quality and reliability of software products, but manual test case creation is labor-intensive. With the rise of large language models (LLMs), there is growing interest in unit test creation with LLMs. However, effective assessment of LLM-generated test cases is limited by the lack of standardized benchmarks that comprehensively cover diverse programming scenarios. To address the assessment of LLM's test case generation ability and lacking dataset for evaluation, we propose the Generated Benchmark from Control-Flow Structure and Variable Usage Composition (GBCV) approach, which systematically generates programs used for evaluating LLMs' test generation capabilities. By leveraging basic control-flow structures and variable usage, GBCV provides a flexible framework to create a spectrum of programs ranging from simple to complex. Because GPT-4o and GPT-3-Turbo are publicly accessible models, to present real-world regular user's use case, we use GBCV to assess LLM performance on them. Our findings indicate that GPT-4o performs better on complex program structures, while all models effectively detect boundary values in simple conditions but face challenges with arithmetic computations. This study highlights the strengths and limitations of LLMs in test generation, provides a benchmark framework, and suggests directions for future improvement.

Recently, deep feedforward neural networks have achieved considerable success in modeling biological sensory processing, in terms of reproducing the input-output map of sensory neurons. However, such models raise profound questions about the very nature of explanation in neuroscience. Are we simply replacing one complex system (a biological circuit) with another (a deep network), without understanding either? Moreover, beyond neural representations, are the deep network's computational mechanisms for generating neural responses the same as those in the brain? Without a systematic approach to extracting and understanding computational mechanisms from deep neural network models, it can be difficult both to assess the degree of utility of deep learning approaches in neuroscience, and to extract experimentally testable hypotheses from deep networks.

I think the rebuttal is prepared very well. Although the assumption of a single component approximating the local decision boundary is quite strong, the paper nonetheless offers a good, systematic approach to interpreting black box ML systems. It is an important topic and I don't see a lot of studies in this area. Overview In an effort to improve scrutability (ability to extract generalizable insight) and explainability of a black box target learning algorithm the current paper proposes to use infinite Dirichlet mixture models with multiple elastic nets (DMM-MEN) to map the inputs to the predicted outputs. Any target model can be approximated by a non-parametric Bayesian regression mixture model.

High-definition road maps play a crucial role in the functionality and verification of highly automated driving functions. These contain precise information about the road network, geometry, condition, as well as traffic signs. Despite their importance for the development and evaluation of driving functions, the generation of high-definition maps is still an ongoing research topic. While previous work in this area has primarily focused on the accuracy of road geometry, we present a novel approach for automated large-scale map generation for use in industrial applications. Our proposed method leverages a minimal number of external information about the road to process LiDAR data in segments. These segments are subsequently combined, enabling a flexible and scalable process that achieves high-definition accuracy. Additionally, we showcase the use of the resulting OpenDRIVE in driving function simulation.

Convolutional neural networks (CNNs) have achieved significant popularity, but their computational and memory intensity poses challenges for resource-constrained computing systems, particularly with the prerequisite of real-time performance. To release this burden, model compression has become an important research focus. Many approaches like quantization, pruning, early exit, and knowledge distillation have demonstrated the effect of reducing redundancy in neural networks. Upon closer examination, it becomes apparent that each approach capitalizes on its unique features to compress the neural network, and they can also exhibit complementary behavior when combined. To explore the interactions and reap the benefits from the complementary features, we propose the Chain of Compression, which works on the combinational sequence to apply these common techniques to compress the neural network. Validated on the image-based regression and classification networks across different data sets, our proposed Chain of Compression can significantly compress the computation cost by 100-1000 times with ignorable accuracy loss compared with the baseline model.

Ensemble learning has been a focal point of machine learning research due to its potential to improve predictive performance. This study revisits the foundational work on ensemble error decomposition, historically confined to bias-variance-covariance analysis for regression problems since the 1990s. Recent advancements introduced a "unified theory of diversity," which proposes an innovative bias-variance-diversity decomposition framework. Leveraging this contemporary understanding, our research systematically explores the application of this decomposition to guide the creation of new ensemble learning algorithms. Focusing on regression tasks, we employ neural networks as base learners to investigate the practical implications of this theoretical framework. This approach used 7 simple ensemble methods, we name them strategies, for neural networks that were used to generate 21 new ensemble algorithms. Among these, most of the methods aggregated with the snapshot strategy, one of the 7 strategies used, showcase superior predictive performance across diverse datasets w.r.t. the Friedman rank test with the Conover post-hoc test. Our systematic design approach contributes a suite of effective new algorithms and establishes a structured pathway for future ensemble learning algorithm development.