Machine Learning (ML) Latest News and Trending articles from all top sources only on Techminis

A naukri.com initiative

New

Home

ML News

Arxiv

134

Image Credit: Arxiv

Data-driven worker activity recognition and picking efficiency estimation in manual strawberry harvesting

A practical system was developed to calculate the efficiency of pickers in commercial strawberry harvesting.
Instrumented picking carts were used to record real-time data of harvested fruit weight, geo-location, and cart movement.
A CNN-LSTM-based deep neural network was trained to classify a picker's activity into 'Pick' and 'NoPick' classes.
The technology could aid growers in automated worker activity monitoring and harvest optimization, ultimately enhancing overall harvest efficiency.

Read Full Article

8 Likes

Arxiv

221

Image Credit: Arxiv

Harnessing uncertainty when learning through Equilibrium Propagation in neural networks

Equilibrium Propagation (EP) is a supervised learning algorithm that trains network parameters using local neuronal activity.
EP avoids data movement, making it suitable for energy-efficient training on neuromorphic systems.
EP can learn on hardware with physical uncertainties, providing implications for self-learning systems.
Research shows successful training of deep neural networks using EP in the presence of uncertainties.

Read Full Article

13 Likes

Arxiv

201

Image Credit: Arxiv

Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models

State Space Models (SSMs) are gaining popularity as an alternative to Transformers due to their memory usage and performance benefits.
Quamba2 is a post-training quantization framework for selective SSMs that enables scaling on various platforms.
Quamba2 offers bit-width configurations of W8A8, W4A8, and W4A16, catering to different usage scenarios.
Experimental results show that Quamba2-8B outperforms other SSM quantization methods, offering significant speed-ups and memory reduction with a minimal accuracy drop.

Read Full Article

12 Likes

Arxiv

312

Image Credit: Arxiv

Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models

Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents.
The introduction of "Task Tokens" provides a method to tailor BFMs to specific tasks while maintaining flexibility.
Task Tokens leverage the transformer architecture of BFMs to learn a task-specific encoder through reinforcement learning, allowing the incorporation of user-defined priors and balancing reward design.
Task Tokens demonstrate efficacy in various tasks, including out-of-distribution scenarios, and are compatible with other prompting modalities.

Read Full Article

18 Likes

Discover more

Arxiv

339

Image Credit: Arxiv

Learning Library Cell Representations in Vector Space

Lib2Vec is a self-supervised framework for learning vector representations of library cells.
The framework includes regularity tests, self-supervised learning, and an attention-based model architecture.
Experimental results show that Lib2Vec captures functional and electrical similarities.
Lib2Vec improves circuit learning applications, especially with limited labeled data.

Read Full Article

20 Likes

Arxiv

328

Image Credit: Arxiv

FairSAM: Fair Classification on Corrupted Data Through Sharpness-Aware Minimization

Image classification models trained on clean data often suffer from significant performance degradation when exposed to testing corrupted data, such as images with impulse noise, Gaussian noise, or environmental noise.
Robust learning algorithms like Sharpness-Aware Minimization (SAM) have shown promise in improving overall model robustness and generalization, but they fall short in addressing biased performance degradation across demographic subgroups.
FairSAM introduces a novel metric to assess performance degradation across subgroups under data corruption and integrates fairness-oriented strategies into SAM.
Experiments demonstrate that FairSAM reconciles robustness and fairness, offering a structured solution for equitable and resilient image classification in the presence of data corruption.

Read Full Article

19 Likes

Arxiv

347

Image Credit: Arxiv

Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification, An Interpretable Multi-Omics Approach

This study introduces the Multi-Omics Graph Kolmogorov-Arnold Network (MOGKAN), a deep learning model that integrates messenger RNA, micro RNA sequences, and DNA methylation data with Protein-Protein Interaction (PPI) networks for accurate and interpretable cancer classification across 31 cancer types.
MOGKAN achieves classification accuracy of 96.28 percent and demonstrates low experimental variability with a standard deviation that is reduced by 1.58 to 7.30 percents compared to Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs).
The biomarkers identified by MOGKAN have been validated as cancer-related markers through Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis.
The proposed model presents an ability to uncover molecular oncogenesis mechanisms by detecting phosphoinositide-binding substances and regulating sphingolipid cellular processes.

Read Full Article

20 Likes

Arxiv

181

Image Credit: Arxiv

MNT-TNN: Spatiotemporal Traffic Data Imputation via Compact Multimode Nonlinear Transform-based Tensor Nuclear Norm

Imputation of random or non-random missing data is a long-standing research topic and a crucial application for Intelligent Transportation Systems (ITS).
A novel spatiotemporal traffic imputation method, Multimode Nonlinear Transformed Tensor Nuclear Norm (MNT-TNN), is proposed to address the challenges in random missing value imputation and spatiotemporal dependency modeling.
MNT-TNN utilizes the Transform-based Tensor Nuclear Norm (TTNN) optimization framework, extending it to a multimode transform with nonlinear activation to capture spatiotemporal correlations and low-rankness of the traffic tensor.
Experimental results show that MNT-TNN and its enhancement framework, ATTNNs, outperform existing imputation methods for random missing traffic value imputation.

Read Full Article

10 Likes

Arxiv

292

Image Credit: Arxiv

Multimodal machine learning with large language embedding model for polymer property prediction

Contemporary large language models (LLMs) like GPT-4 and Llama, combined with molecular structure embeddings, enable accurate prediction of polymer properties.
PolyLLMem, a multimodal architecture, integrates text embeddings from Llama 3 with molecular structure embeddings derived from Uni-Mol.
Low-rank adaptation (LoRA) layers are incorporated to refine the embeddings based on limited polymer dataset, enhancing their chemical relevance.
PolyLLMem's performance is comparable to graph-based and transformer-based models, even with limited training data, accelerating the discovery of advanced polymeric materials.

Read Full Article

17 Likes

Arxiv

Image Credit: Arxiv

Enhancing Federated Learning Through Secure Cluster-Weighted Client Aggregation

Federated learning (FL) is a promising paradigm in machine learning that enables collaborative model training across decentralized devices without sharing raw data.
The heterogeneous nature of local datasets in FL can cause model performance discrepancies, convergence challenges, and privacy concerns.
A novel FL framework called ClusterGuardFL is introduced, which uses dissimilarity scores, k-means clustering, and reconciliation confidence scores to assign weights to client updates.
Experimental results show that ClusterGuardFL improves model performance in diverse datasets.

Read Full Article

Arxiv

166

Image Credit: Arxiv

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used for privacy-preserving deep learning.
The selection of the optimal clipping threshold C in DP-SGD poses a challenge, resulting in privacy and computational overhead.
A new framework called Dynamic Clipping DP-SGD (DC-SGD) is proposed, leveraging differentially private histograms to estimate gradient norm distributions and adjust the clipping threshold C dynamically.
Experimental results show that DC-SGD achieves up to 9 times acceleration in hyperparameter tuning compared to DP-SGD, with improved accuracy and privacy guarantees.

Read Full Article

9 Likes

Arxiv

288

Image Credit: Arxiv

AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks

Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness.
Certified robustness based on randomized smoothing has emerged as a promising solution, offering provable guarantees that a model's predictions remain stable under adversarial perturbations.
The proposed framework, AuditVotes, integrates randomized smoothing with augmentation and conditional smoothing to improve data quality and prediction consistency.
Experimental results demonstrate that AuditVotes significantly enhances clean accuracy, certified robustness, and empirical robustness for GNNs.

Read Full Article

17 Likes

Arxiv

114

Image Credit: Arxiv

Buyer-Initiated Auction Mechanism for Data Redemption in Machine Unlearning

The rapid growth of artificial intelligence (AI) has raised privacy concerns over user data.
Machine unlearning allows AI service providers to remove user data from trained models and training datasets to comply with privacy regulations like GDPR and CCPA.
To balance the cost of unlearning and privacy protection, a buyer-initiated auction mechanism for data redemption is proposed.
The mechanism enables service providers to purchase data from willing users with appropriate compensation, maximizing social welfare.

Read Full Article

6 Likes

Arxiv

118

Image Credit: Arxiv

Learning Structure-enhanced Temporal Point Processes with Gromov-Wasserstein Regularization

Real-world event sequences often have clustering structures, but most existing temporal point processes (TPPs) ignore them.
A new study proposes learning structure-enhanced TPPs with Gromov-Wasserstein (GW) regularization.
The proposed method imposes clustering structures on TPPs for improved interpretability in modeling and prediction.
The learned TPPs demonstrate clustered sequence embeddings and competitive predictive and clustering performance.

Read Full Article

7 Likes

Arxiv

249

Image Credit: Arxiv

MSNGO: multi-species protein function annotation based on 3D protein structure and network propagation

Protein function prediction has improved using high-precision protein structures predicted by AlphaFold2.
A new model called MSNGO integrates structural features and network propagation methods for multi-species protein function prediction.
Using structural features significantly enhances the accuracy of multi-species protein function prediction.
MSNGO outperforms previous methods relying on sequence features and protein-protein interaction networks.

Read Full Article

14 Likes

For uninterrupted reading, download the app