Devendra Singh Dhami
YOU?
Author Swipe
View article: Aster peduncularis Wall. Ex. Nees: in-vitro antibacterial and antileishmanial activities of essential oil from India
Aster peduncularis Wall. Ex. Nees: in-vitro antibacterial and antileishmanial activities of essential oil from India Open
This study examined the antibacterial and antileishmanial activities of the essential oil extracted from the Aster peduncularis Wall. Ex Nees. The antibacterial activity of this essential oil was studied against five human pathogen bacteri…
View article: The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents
The Constitutional Controller: Doubt-Calibrated Steering of Compliant Agents Open
Ensuring reliable and rule-compliant behavior of autonomous agents in uncertain environments remains a fundamental challenge in modern robotics. Our work shows how neuro-symbolic systems, which integrate probabilistic, symbolic white-box r…
View article: Elucidating linear programs by neural encodings
Elucidating linear programs by neural encodings Open
Linear Programs (LPs) are one of the major building blocks of AI and have championed recent strides in differentiable optimizers for learning systems. While efficient solvers exist for even high-dimensional LPs, explaining their solutions …
View article: Causal Explanations Over Time: Articulated Reasoning for Interactive Environments
Causal Explanations Over Time: Articulated Reasoning for Interactive Environments Open
Structural Causal Explanations (SCEs) can be used to automatically generate explanations in natural language to questions about given data that are grounded in a (possibly learned) causal model. Unfortunately they work for small data only.…
View article: Hybrid Many-Objective Optimization in Probabilistic Mission Design for Compliant and Effective UAV Routing
Hybrid Many-Objective Optimization in Probabilistic Mission Design for Compliant and Effective UAV Routing Open
Advanced Aerial Mobility encompasses many outstanding applications that promise to revolutionize modern logistics and pave the way for various public services and industry uses. However, throughout its history, the development of such syst…
View article: Aster peduncularis Wall. Ex. Nees: In- Vitro Antibacterial and Antileishmanial Activities of Essential oil from India
Aster peduncularis Wall. Ex. Nees: In- Vitro Antibacterial and Antileishmanial Activities of Essential oil from India Open
The study examined the antibacterial and antileishmanial properties of the essential oil extracted from Aster peduncularis Wall. Ex Nees. The antibacterial activity of this essential oil was studied using disk diffusion and broth microdilu…
View article: Scaling Probabilistic Circuits via Data Partitioning
Scaling Probabilistic Circuits via Data Partitioning Open
Probabilistic circuits (PCs) enable us to learn joint distributions over a set of random variables and to perform various probabilistic queries in a tractable fashion. Though the tractability property allows PCs to scale beyond non-tractab…
View article: Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data
Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data Open
Causality in time series can be challenging to determine, especially in the presence of non-linear dependencies. Granger causality helps analyze potential relationships between variables, thereby offering a method to determine whether one …
View article: Probabilistic Mission Design in Neuro-Symbolic Systems
Probabilistic Mission Design in Neuro-Symbolic Systems Open
Advanced Air Mobility (AAM) is a growing field that demands accurate modeling of legal concepts and restrictions in navigating intelligent vehicles. In addition, any implementation of AAM needs to face the challenges posed by inherently dy…
View article: StaR Maps: Unveiling Uncertainty in Geospatial Relations
StaR Maps: Unveiling Uncertainty in Geospatial Relations Open
The growing complexity of intelligent transportation systems and their applications in public spaces has increased the demand for expressive and versatile knowledge representation. While various mapping efforts have achieved widespread cov…
View article: The Constitutional Filter
The Constitutional Filter Open
Predictions in environments where a mix of legal policies, physical limitations, and operational preferences impacts an agent's motion are inherently difficult. Since Neuro-Symbolic systems allow for differentiable information flow between…
View article: Answer Set Networks: Casting Answer Set Programming into Deep Learning
Answer Set Networks: Casting Answer Set Programming into Deep Learning Open
Although Answer Set Programming (ASP) allows constraining neural-symbolic (NeSy) systems, its employment is hindered by the prohibitive costs of computing stable models and the CPU-bound nature of state-of-the-art solvers. To this end, we …
View article: Graph Neural Networks Need Cluster-Normalize-Activate Modules
Graph Neural Networks Need Cluster-Normalize-Activate Modules Open
Graph Neural Networks (GNNs) are non-Euclidean deep learning models for graph-structured data. Despite their successful and diverse applications, oversmoothing prohibits deep architectures due to node features converging to a single fixed …
View article: Learning differentiable logic programs for abstract visual reasoning
Learning differentiable logic programs for abstract visual reasoning Open
Visual reasoning is essential for building intelligent agents that understand the world and perform problem-solving beyond perception. Differentiable forward reasoning has been developed to integrate reasoning with gradient-based machine l…
View article: Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad? Open
Recently, newly developed Vision-Language Models (VLMs), such as OpenAI's o1, have emerged, seemingly demonstrating advanced reasoning capabilities across text and image modalities. However, the depth of these advances in language-guided p…
View article: xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories Open
Time series data is prevalent across numerous fields, necessitating the development of robust and accurate forecasting models. Capturing patterns both within and between temporal and multivariate components is crucial for reliable predicti…
View article: Forecasting Company Fundamentals
Forecasting Company Fundamentals Open
Company fundamentals are key to assessing companies' financial and overall success and stability. Forecasting them is important in multiple fields, including investing and econometrics. While statistical and contemporary machine learning m…
View article: Systems with Switching Causal Relations: A Meta-Causal Perspective
Systems with Switching Causal Relations: A Meta-Causal Perspective Open
Most work on causality in machine learning assumes that causal relationships are driven by a constant underlying process. However, the flexibility of agents' actions or tipping points in the environmental process can change the qualitative…
View article: BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
BlendRL: A Framework for Merging Symbolic and Neural Policy Learning Open
Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and r…
View article: Neuro-symbolic Predicate Invention: Learning relational concepts from visual scenes
Neuro-symbolic Predicate Invention: Learning relational concepts from visual scenes Open
The predicates used for Inductive Logic Programming (ILP) systems are usually elusive and need to be hand-crafted in advance, which limits the generalization of the system when learning new rules without sufficient background knowledge. Pr…
View article: $χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
$χ$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains Open
Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and propose Characteristic Interventional Sum-Product Network ($χ$S…
View article: EXPIL: Explanatory Predicate Invention for Learning in Games
EXPIL: Explanatory Predicate Invention for Learning in Games Open
Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's a…
View article: Towards Probabilistic Clearance, Explanation and Optimization
Towards Probabilistic Clearance, Explanation and Optimization Open
Employing Unmanned Aircraft Systems (UAS) beyond visual line of sight (BVLOS) is an endearing and challenging task. While UAS have the potential to significantly enhance today's logistics and emergency response capabilities, unmanned flyin…
View article: Machine learning meets Kepler: inverting Kepler’s equation for All vs All conjunction analysis
Machine learning meets Kepler: inverting Kepler’s equation for All vs All conjunction analysis Open
The number of satellites in orbit around Earth is increasing rapidly, with the risk of collision rising accordingly. Trends of the global population of satellites need to be analyzed to test the viability and impact of proposed rules and l…
View article: United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once
United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once Open
In natural language processing and vision, pretraining is utilized to learn effective representations. Unfortunately, the success of pretraining does not easily carry over to time series due to potential mismatch between sources and target…
View article: DeiSAM: Segment Anything with Deictic Prompting
DeiSAM: Segment Anything with Deictic Prompting Open
Large-scale, pre-trained neural networks have demonstrated strong capabilities in various tasks, including zero-shot image segmentation. To identify concrete objects in complex scenes, humans instinctively rely on deictic descriptions in n…