Episodic memory supports the acquisition of structured task representations

Lu, Q., Hummos, A., Norman, K. A. Edit "Episodic memory supports the acquisition of structured task representations"
Generalization to new tasks requires learning of task representations that accurately reflect the similarity structure of the task space. Here, we argue that episodic memory (EM) plays an essential role in this process by stabilizing task representations, thereby supporting the accumulation of structured knowledge. We demonstrate this using a neural network model that infers task representations that minimize the current task's objective function; crucially, the model can retrieve previously encoded task representations from EM and use these to initialize the task inference process. With EM, the model succeeds in learning the underlying task structure; without EM, task representations drift and the network fails to learn the structure. We further show that EM errors can support structure learning by promoting the activation of similar task representations in tasks with similar sensory inputs. Overall, this model provides a novel account of how EM supports the acquisition of structured task representations.

CG-FHAUI: an efficient algorithm for simultaneously mining succinct pattern sets of frequent high average utility itemsets

Latest Results for Knowledge and Information Systems Edit "CG-FHAUI: an efficient algorithm for simultaneously mining succinct pattern sets of frequent high average utility itemsets"

Abstract

The identification of both closed frequent high average utility itemsets (CFHAUIs) and generators of frequent high average utility itemsets (GFHAUIs) has substantial significance because they play an essential and concise role in representing frequent high average utility itemsets (FHAUIs). These concise summaries offer a compact yet crucial overview that can be much smaller. In addition, they allow the generation of non-redundant high average utility association rules, a crucial factor for decision-makers to consider. However, difficulty arises from the complexity of discovering these representations, primarily because the average utility function does not satisfy both monotonic and anti-monotonic properties within each equivalence class, that is for itemsets sharing the same subset of transactions. To tackle this challenge, this paper proposes an innovative method for efficiently extracting CFHAUIs and GFHAUIs. This approach introduces novel bounds on the average utility, including a weak lower bound called \(wlbau\) and a lower bound named \(auvlb\) . Efficient pruning strategies are also designed with the aim of early elimination of non-closed and/or non-generator FHAUIs based on the \(wlbau\) and \(auvlb\) bounds, leading to quicker execution and lower memory consumption. Additionally, the paper introduces a novel algorithm, CG-FHAUI, designed to concurrently discover both GFHAUIs and CFHAUIs. Empirical results highlight the superior performance of the proposed algorithm in terms of runtime, memory usage, and scalability when compared to a baseline algorithm.

A Rate-Distortion-Classification Approach for Lossy Image Compression

Yuefeng Zhang Edit "A Rate-Distortion-Classification Approach for Lossy Image Compression"
arXiv:2405.03500v1 Announce Type: new Abstract: In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized the significance of considering semantic distortion in compressed images. To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression, offering a unified framework to optimize the trade-off between rate, distortion, and classification accuracy. The RDC model is extensively analyzed both statistically on a multi-distribution source and experimentally on the widely used MNIST dataset. The findings reveal that the RDC model exhibits desirable properties, including monotonic non-increasing and convex functions, under certain conditions. This work provides insights into the development of human-machine friendly compression methods and Video Coding for Machine (VCM) approaches, paving the way for end-to-end image compression techniques in real-world applications.

Ih Block Reveals Separation of Timescales in Pyloric Rhythm Response to Temperature Changes in Cancer borealis

Schapiro, K., Rittenberg, J., Kenngott, M., Marder, E. Edit "Ih Block Reveals Separation of Timescales in Pyloric Rhythm Response to Temperature Changes in Cancer borealis"
Motor systems operate over a range of frequencies and relative timing (phase). We studied the contribution of the hyperpolarization-activated inward current (Ih) to frequency and phase in the pyloric rhythm of the stomatogastric ganglion (STG) of the crab, Cancer borealis as temperature was altered from 11 degrees C to 21 degrees C. Under control conditions, the frequency of the rhythm increased monotonically with temperature, while the phases of the pyloric dilator (PD), lateral pyloric (LP), and pyloric (PY) neurons remained constant. When we blocked Ih> with cesium (Cs+) PD offset, LP onset, and LP offset were all phase advanced in Cs+ at 11 degrees C, and the latter two further advanced as temperature increased. In Cs+ the steady state increase in pyloric frequency with temperature diminished and the Q10 of the pyloric frequency dropped from ~1.75 to ~1.35. Unexpectedly in Cs+, the frequency displayed non-monotonic dynamics during temperature transitions; the frequency initially dropped as temperature increased, then rose once temperature stabilized, creating a characteristic jag. Interestingly, these jags were still present during temperature transitions in Cs+ when the pacemaker was isolated by picrotoxin, although the temperature-induced change in frequency recovered to control levels. Overall, these data suggest that Ih plays an important role in the ability of this circuit to produces smooth transitory responses and persistent frequency increases by different mechanisms during temperature fluctuations.

Novel clock neuron subtypes regulate temporal aspects of sleep

Ma, D., Le, J. Q., Dai, X., Diaz, M., Abruzzi, K., Rosbash, M. Edit "Novel clock neuron subtypes regulate temporal aspects of sleep"
Circadian neurons within animal brains orchestrate myriad physiological processes and behaviors, But the contribution of these neurons to the regulation of sleep is not well understood. To address this deficiency, we leveraged single cell RNA sequencing to generate a new and now comprehensive census of transcriptomic cell types of Drosophila clock neurons. We focused principally on the enigmatic DN3s, which constitute about half of the 75 pairs of clock neurons in the fly brain and were previously almost completely uncharacterized. These DN3s are organized into 12 clusters with unusual gene expression features compared to the more well-studied clock neurons. We further show that different DN3 subtypes with distinct projection patterns promote sleep at specific times of the day through a common G protein coupled receptor, TrissinR. Our findings indicate an intricate regulation of sleep behavior by clock neurons and highlight their remarkable diversity in gene expression, projection patterns and functional properties.

DeepLeMiN: Deep-learning-empowered Physics-aware Lensless Miniscope

Tian, F., Mattison, B., Yang, W. Edit "DeepLeMiN: Deep-learning-empowered Physics-aware Lensless Miniscope"
Mask-based lensless fluorescence microscopy is a compact, portable imaging technique promising for biomedical research. It forms images through a thin optical mask near the camera without bulky optics, enabling snapshot three-dimensional imaging and a scalable field of view (FOV) without increasing device thickness. Lensless microscopy relies on computational algorithms to solve the inverse problem of object reconstruction. However, there has been a lack of efficient reconstruction algorithms for large-scale data. Furthermore, the entire FOV is typically reconstructed as a whole, which demands substantial computational resources and limits the scalability of the FOV. Here, we developed DeepLeMiN, a lensless microscope with a custom designed optical mask and a multi-stage physics-informed deep learning model. This not only enables the reconstruction of localized FOVs, but also significantly reduces the computational resource demands and facilitates real-time reconstruction. Our deep learning algorithm can reconstruct object volumes over 4x6x0.6 mm3, achieving lateral and axial resolution of ~10 m and ~50 m respectively. We demonstrated significant improvement in both reconstruction quality and speed compared to traditional methods, across various fluorescent samples with dense structures. Notably, we achieved high-quality reconstruction of 3D motion of hydra and the neuronal activity with cellular resolution in awake mouse cortex. DeepLeMiN holds great promise for scalable, large FOV, real-time, 3D imaging applications with compact device footprint.

Skew Multiple Scaled Mixtures of Normal Distributions with Flexible Tail Behavior and Their Application to Clustering

Latest Results for Journal of Classification Edit "Skew Multiple Scaled Mixtures of Normal Distributions with Flexible Tail Behavior and Their Application to Clustering"

Abstract

The family of multiple scaled mixtures of multivariate normal (MSMN) distributions has been shown to be a powerful tool for modeling data that allow different marginal amounts of tail weight. An extension of the MSMN distribution is proposed through the incorporation of a vector of shape parameters, resulting in the skew multiple scaled mixtures of multivariate normal (SMSMN) distributions. The family of SMSMN distributions can express a variety of shapes by controlling different degrees of tailedness and versatile skewness in each dimension. Some characterizations and probabilistic properties of the SMSMN distributions are studied and an extension to finite mixtures thereof is also discussed. Based on a sort of selection mechanism, a feasible ECME algorithm is designed to compute the maximum likelihood estimates of model parameters. Numerical experiments on simulated data and three real data examples demonstrate the efficacy and usefulness of the proposed methodology.

The Role of Human Factors in the LastPass Breach

Niroop Sugunaraj Edit "The Role of Human Factors in the LastPass Breach"
arXiv:2405.01795v1 Announce Type: new Abstract: This paper examines the complex nature of cyber attacks through an analysis of the LastPass breach. It argues for the integration of human-centric considerations into cybersecurity measures, focusing on mitigating factors such as goal-directed behavior, cognitive overload, human biases (e.g., optimism, anchoring), and risky behaviors. Findings from an analysis of this breach offers support to the perspective that addressing both the human and technical dimensions of cyber defense can significantly enhance the resilience of cyber systems against complex threats. This means maintaining a balanced approach while simultaneously simplifying user interactions, making users aware of biases, and discouraging risky practices are essential for preventing cyber incidents.

The Mercurial Top-Level Ontology of Large Language Models

Nele K\"ohler, Fabian Neuhaus Edit "The Mercurial Top-Level Ontology of Large Language Models"
arXiv:2405.01581v1 Announce Type: new Abstract: In our work, we systematize and analyze implicit ontological commitments in the responses generated by large language models (LLMs), focusing on ChatGPT 3.5 as a case study. We investigate how LLMs, despite having no explicit ontology, exhibit implicit ontological categorizations that are reflected in the texts they generate. The paper proposes an approach to understanding the ontological commitments of LLMs by defining ontology as a theory that provides a systematic account of the ontological commitments of some text. We investigate the ontological assumptions of ChatGPT and present a systematized account, i.e., GPT's top-level ontology. This includes a taxonomy, which is available as an OWL file, as well as a discussion about ontological assumptions (e.g., about its mereology or presentism). We show that in some aspects GPT's top-level ontology is quite similar to existing top-level ontologies. However, there are significant challenges arising from the flexible nature of LLM-generated texts, including ontological overload, ambiguity, and inconsistency.

HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models

Tanmay Sen, Ansuman Das, Mrinmay Sen Edit "HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models"
arXiv:2405.01577v1 Announce Type: new Abstract: Hate speech encompasses verbal, written, or behavioral communication that targets derogatory or discriminatory language against individuals or groups based on sensitive characteristics. Automated hate speech detection plays a crucial role in curbing its propagation, especially across social media platforms. Various methods, including recent advancements in deep learning, have been devised to address this challenge. In this study, we introduce HateTinyLLM, a novel framework based on fine-tuned decoder-only tiny large language models (tinyLLMs) for efficient hate speech detection. Our experimental findings demonstrate that the fine-tuned HateTinyLLM outperforms the pretrained mixtral-7b model by a significant margin. We explored various tiny LLMs, including PY007/TinyLlama-1.1B-step-50K-105b, Microsoft/phi-2, and facebook/opt-1.3b, and fine-tuned them using LoRA and adapter methods. Our observations indicate that all LoRA-based fine-tuned models achieved over 80\% accuracy.