Machine Learning-Guided Protein Engineering

ACS Catalysis, Journal Year: 2023, Volume and Issue: 13(21), P. 13863 - 13895

Published: Oct. 13, 2023

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid the discovery annotation of enzymes, as well suggesting beneficial mutations for improving known targets. The field protein is gathering steam, driven by recent success stories notable other areas. It already encompasses ambitious tasks such understanding predicting structure function, catalytic efficiency, enantioselectivity, dynamics, stability, solubility, aggregation, more. Nonetheless, still evolving, with many challenges overcome questions address. In this Perspective, we provide an overview ongoing trends domain, highlight case studies, examine current limitations learning-based We emphasize crucial importance thorough validation emerging models before their use rational design. present our opinions on fundamental problems outline potential directions future research.

Language: Английский

---

Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Journal Year: 2023, Volume and Issue: unknown

Published: June 1, 2023

Model-based deep learning has achieved astounding successes due in part to the availability of large-scale real-world data. However, processing such massive amounts data comes at a considerable cost terms computations, storage, training and search for good neural architectures. Dataset distillation thus recently come fore. This paradigm involves distilling information from large datasets into tiny compact synthetic that latter ideally yields similar performances as former. State-of-the-art methods primarily rely on dataset by matching gradients obtained during between real these gradient-matching suffer so-called accumulated trajectory error caused discrepancy subsequent evaluation. To mitigate adverse impact this error, we propose novel approach encourages optimization algorithm seek flat trajectory. We show weights trained are robust against errors perturbations with regularization towards Our method, called Flat Trajectory Distillation (FTD), is shown boost performance up 4.7% subset images ImageNet higher resolution images. also validate effectiveness generalizability our method different resolutions demonstrate its applicability architecture search. Code available at. https://github.com/AngusDujw/FTD-distillation.

Language: Английский

---

Data-Centric Green Artificial Intelligence: A Survey

IEEE Transactions on Artificial Intelligence, Journal Year: 2023, Volume and Issue: 5(5), P. 1973 - 1989

Published: Sept. 14, 2023

With the exponential growth of computational power and availability large-scale datasets in recent years, remarkable advancements have been made field artificial intelligence (AI), leading to complex models innovative applications. However, these consume a significant unprecedented amount energy, contributing greenhouse gas emissions growing carbon footprint AI industry. In response, concept green has emerged, prioritizing energy efficiency sustainability alongside accuracy related measures. To this end, data-centric approaches are very promising reduce consumption algorithms. This paper presents comprehensive overview technologies their impact on Specifically, it focuses methods that utilize training data an efficient manner improve We identified multiple approaches, such as active learning, knowledge transfer/sharing, dataset distillation, augmentation, curriculum learning can contribute development environmentally-friendly implementations machine Finally, practical applications highlighted, challenges future directions discussed.

Language: Английский

---

Advanced Deep Learning Models for 6G: Overview, Opportunities and Challenges

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 133245 - 133314

Published: Jan. 1, 2024

The advent of the sixth generation mobile communications (6G) ushers in an era heightened demand for advanced network intelligence to tackle challenges expanding landscape and increasing service demands. Deep Learning (DL), as a crucial technique instilling into 6G, has demonstrated powerful promising development. This paper provides comprehensive overview pivotal role DL exploring myriad opportunities that arise. Firstly, we present detailed vision emphasizing areas such adaptive resource allocation, intelligent management, robust signal processing, ubiquitous edge intelligence, endogenous security. Secondly, this reviews how models leverage their unique learning capabilities solve complex demands 6G. discussed include Convolutional Neural Networks (CNN), Generative Adversarial (GAN), Graph (GNN), Reinforcement (DRL), Transformer, Federated (FL), Meta Learning. Additionally, examine specific each model faces within 6G context. Moreover, delve rapidly evolving field Artificial Intelligence Generated Content (AIGC), examining its development impact framework. Finally, culminates discussion ten critical open problems integrating with setting stage future research field.

Language: Английский

---

Knowledge fusion distillation and gradient-based data distillation for class-incremental learning

Neurocomputing, Journal Year: 2025, Volume and Issue: 622, P. 129286 - 129286

Published: Jan. 5, 2025

Language: Английский

---

ECODI: a novel evolutionary coreset distillation with LLM-assisted fitness evaluation for encrypted network traffics

International Journal of Machine Learning and Cybernetics, Journal Year: 2025, Volume and Issue: unknown

Published: March 14, 2025

Language: Английский

---

Brain-Inspired Continual Learning: Robust Feature Distillation and Re-Consolidation for Class Incremental Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 34054 - 34073

Published: Jan. 1, 2024

Artificial intelligence and neuroscience have a long intertwined history. Advancements in research significantly influenced the development of artificial systems that potential to retain knowledge akin humans. Building upon foundational insights from existing adversarial continual learning fields, we introduce novel framework comprises two key concepts: feature distillation re-consolidation. The distills (CL) robust features rehearses them while next task, aiming replicate mammalian brain's process consolidating memories through rehearsing distilled version waking experiences. Furthermore, proposed emulates mechanism memory re-consolidation, where experiences influence assimilation previous via This incorporates new understanding CL model after current task into CL-robust samples task(s) mitigate catastrophic forgetting. framework, called Robust Rehearsal, circumvents limitations frameworks rely on availability pre-trained Oracle models pre-distill CL-robustified datasets for training subsequent models. We conducted extensive experiments three datasets, CIFAR10, CIFAR100, real-world helicopter attitude demonstrating trained using Rehearsal outperform their counterparts' baseline methods. In addition, series assess impact changing sizes number tasks, methods employing rehearsal other without rehearsal. Lastly, shed light existence diverse features, explore effects various optimization objectives within realms joint, continual, deep neural networks. Our findings indicate objective dictates learning, which plays vital role performance. Such observation further emphasizes importance alleviating our experiments, closely following can contribute developing approaches long-standing challenge

Language: Английский

---

TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation

Published: April 22, 2025

In the era of data-centric AI, focus recommender systems has shifted from model-centric innovations to approaches. The success modern AI models is built on large-scale datasets, but this also results in significant training costs. Dataset distillation emerged as a key solution, condensing large datasets accelerate model while preserving performance. However, discrete and sequentially correlated user-item interactions, particularly with extensive item sets, presents considerable challenges. This paper introduces \textbf{TD3}, novel \textbf{T}ucker \textbf{D}ecomposition based \textbf{D}ataset \textbf{D}istillation method within meta-learning framework, designed for sequential recommendation. TD3 distills fully expressive \emph{synthetic sequence summary} original data. To efficiently reduce computational complexity extract refined latent patterns, Tucker decomposition decouples summary into four factors: user factor}, \emph{temporal dynamics \emph{shared \emph{relation core} that their interconnections. Additionally, surrogate objective bi-level optimization proposed align feature spaces extracted trained both data synthetic beyond na\"ive performance matching approach. \emph{inner-loop}, an augmentation technique allows learner closely fit summary, ensuring accurate update it \emph{outer-loop}. process address long dependencies, RaT-BPTT employed optimization. Experiments analyses multiple public have confirmed superiority cross-architecture generalizability designs. Codes are released at https://github.com/USTC-StarTeam/TD3.

Language: Английский

---

A study on lightweight algorithms for fabric defect detection

Textile Research Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

In industrial applications where device capacity, computational performance, and thermal management are limited, we propose the YOLOvT-Light model for fabric defect detection. This incorporates convolutional block attention module (CBAM)-EfficientNet backbone network, balancing detection speed precision while significantly reducing complexity maintaining high precision. GhostConv replaces standard convolution in neck section, effectively parameters cost through simple linear transformations. Additionally, integration of Faster Block C2f modules retains local feature fusion capabilities further decreasing computation. Experimental results using DAGM2007 dataset demonstrate that reduces weight size (9.50 MB), computation performance (13.9 Gflops), parameter count (6.11 M) compared with baseline model, improving inference (223 fps), without sacrificing lightweight architecture ensures feasibility deploying on resource-constrained devices, making it suitable real-time, cost-effective, safe textile manufacturing environments. study provides a reliable solution developing efficient, models applicable to real-world settings.

Language: Английский

---

Self-supervised monocular depth learning from unknown cameras: Leveraging the power of raw data

Image and Vision Computing, Journal Year: 2025, Volume and Issue: unknown, P. 105505 - 105505

Published: March 1, 2025

Language: Английский

---