2023-2024 SPLIT + RSD objective convergence graphs by Arnaud Masseron (21769079)

2023-2024 SPLIT + RSD detailed cost graphs by Arnaud Masseron (21769079)

2024-2025 SPLIT + RSD detailed cost graphs by Arnaud Masseron (21769079)

Distribution of the average embeddings. by Yiming Kuang (22120458)

Network Structure of Primary Component Contrastive learning (PiCCL). by Yiming Kuang (22120458)

“…<p>PiCCL is a multiview contrastive learning algorithm, <i>P</i> views are generated from each sample image and fed into a multiplex Siamese network. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

High-Coverage Stereoproteome Mapping Uncovers Pervasive Protein Stereoisomerization Associated with Neurodegeneration by Xia Xu (83500)

“…Here, we introduce an untargeted, <i>de novo</i> STEP discovery protocol for comprehensive STEP profiling and relative quantification. …”

Identification of DEGs and GSEA in two groups. by Taole Li (20490462)

Data Sheet 1_Exploring hypoxia-related genes in spinal cord injury: a pathway to new therapeutic targets.docx by Shihuan Cheng (10279035)

Summary of related works. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

Results on STL-10 at 500 epoch. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

Results on CIFAR-10 & CIFAR-100. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

Speed and Memory Metrics. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

Image augmentation methods. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

Results on STL-10 with batch size = 256. by Yiming Kuang (22120458)

“…To demonstrate its strength, we benchmarked PiCCL against various state-of-the-art self-supervised algorithms on multiple datasets including CIFAR-10, CIFAR-100, and STL-10. …”

General Chemically Intuitive Atom- and Bond-Level DFT Descriptors for Machine Learning Approaches to Reaction Condition Prediction by Miguel Nouman (21557202)

“…We show that by combining structural and general DFT descriptors, models with up to 71% fewer trainable parameter than their purely structural counterparts can provide comparable or superior weighted precision, top-1 and top-3 accuracies. Moreover, we report improvements of up to 5, 10, and 11% in weighted precision, top-1 accuracy and <i>F</i>₁ score, respectively, for neural networks trained on hybrid representations which combine general DFT and structural descriptors, when compared to structural models with equivalent architectures and input sizes. …”