![UCLA Office of Advanced Research Computing (OARC)](/img/default-banner.jpg)
- 130
- 280 585
UCLA Office of Advanced Research Computing (OARC)
United States
เข้าร่วมเมื่อ 10 ม.ค. 2014
The UCLA Office of Advanced Research Computing (OARC) is home to a team of experts who intensify and broaden data-driven research and technology capabilities at UCLA through consultation, training, and collaboration.
How Can One Use Machine Learning and High Performance Computing for Humanities Research?
By Benjamin Winjum, Project Scientist, OARC
December 7, 2023, 10-11AM via Zoom
The application of machine learning (ML) and high performance computing (HPC) to humanities research holds tremendous potential, but there are significant challenges to developing a community of experts that can work together at this intersection of topic and technique. HPC experts may not have the background necessary to appreciate how their tools can best be brought to bear on the diverse datasets and conceptual approaches of humanities researchers, and humanities researchers may not have the well-honed background in computational and statistical modeling that resides with ML or HPC specialists. We will approach this topic by focusing on a few case studies in the humanities that illustrate how ML and HPC can both be used to powerful effect, whether by streamlining the initial processing of massive data, modeling and visualizing humanities-relevant datasets, or using deep learning frameworks and the speed and power of GPUs to rapidly prototype predictive models.
December 7, 2023, 10-11AM via Zoom
The application of machine learning (ML) and high performance computing (HPC) to humanities research holds tremendous potential, but there are significant challenges to developing a community of experts that can work together at this intersection of topic and technique. HPC experts may not have the background necessary to appreciate how their tools can best be brought to bear on the diverse datasets and conceptual approaches of humanities researchers, and humanities researchers may not have the well-honed background in computational and statistical modeling that resides with ML or HPC specialists. We will approach this topic by focusing on a few case studies in the humanities that illustrate how ML and HPC can both be used to powerful effect, whether by streamlining the initial processing of massive data, modeling and visualizing humanities-relevant datasets, or using deep learning frameworks and the speed and power of GPUs to rapidly prototype predictive models.
มุมมอง: 83
วีดีโอ
Panel Discussion on Harnessing High-performance Computing across STEM Disciplines
มุมมอง 52หลายเดือนก่อน
The IDRE Early Career Researchers group's panel is a discussion on how high-performance computing (HPC) is used across STEM disciplines. It is led by the following new cohort of IDRE fellows (2023-2024) from various disciplines across the UCLA campus. Robert Fofrich - Institute of the Environment and Sustainability Fei-man Hsu - Department of Molecular, Cell, and Development Biology Alec Linot ...
TimeAutoDiff : Combining auto-encoder and diffusion model for time series tabular synthesizing
มุมมอง 99หลายเดือนก่อน
Speaker: Najoon Suh, Ph.D IDRE Fellow Department of Statistics and Data Science University of California Los Angeles Abstract: In the work to be presented, we leverage the power of latent diffusion models to generate synthetic time series tabular data. Along with the temporal and feature correlations, the heterogeneous nature of the feature in the table has been one of the main obstacles in tim...
Mitigating climate change drivers and associated risks of surpassing lower emission targets
มุมมอง 1882 หลายเดือนก่อน
Robert Fofrich, Ph.D. IDRE and UC President’s Postdoctoral Fellow Institute of the Environment and Sustainability University of California Los Angeles Abstract: Lower climate change mitigation pathways require large and swift reductions in anthropogenic CO2 emissions worldwide, a substantial portion arising from fossil energy sources utilized in electricity generation. Thus, stabilizing global ...
2024 International Humanitarian Mapathon MariahTso Keynote
มุมมอง 743 หลายเดือนก่อน
The 2024 International Humanitarian Mapathon kicks off a remarkable keynote from Mariah Tso. She set the stage for our mapping activities and why we map. Her talk also helped put into context the student protests in support of Gaza that were happening all across the United States as the mapathon began and continued. This was especially meaningful as two of our organizing schools - USC and UCLA ...
Using Topological Data Analysis to characterize fluctuations in brain activity patterns
มุมมอง 2044 หลายเดือนก่อน
Speaker: Prof. Manish Sagger Tashia and John Morgridge Endowed Faculty Scholar in Pediatric Translational Medicine, Stanford Maternal & Child Health Research Institute Assistant Professor, Department of Psychiatry & Behavioral Sciences Principal Investigator, Brain Dynamics Lab Stanford University School of Medicine Abstract: Understanding the neurobiological underpinnings of psychiatric disord...
Interacting Dynamical System Modeling for Science: Construction and Generalization
มุมมอง 944 หลายเดือนก่อน
Abstract: Many real-world systems such as disease transmission, molecular dynamics, and spring systems can be considered as multi-agent dynamical systems, where multiple objects interact with each other and exhibit complex behavior along the time. In this talk, I will discuss my current research on interacting dynamics system modeling for scientific problems, especially focusing on model constr...
Introduction to Meta-analysis using Stata
มุมมอง 1.3K5 หลายเดือนก่อน
This workshop introduces the ideas used in meta-analysis, including how to collect and organize data, how to run a basic meta-analysis, and how to interpret the output.
Annotate Digital Imagery: Theory, Applied Practice, and Tools for Research
มุมมอง 745 หลายเดือนก่อน
Information systems since the advent of the World Wide Web have offered increasingly sophisticated and reliable tools for inquiry and scholarship based upon centuries-old practices of annotation. What are the connections and tensions between visual and verbal media? How do idiosyncratic readerly practices of scribbling in margins of a book translate into W3C standards for networked multimedia s...
Computational approaches in clinical epigenomics
มุมมอง 985 หลายเดือนก่อน
Speaker: Fei-Man Hsu, Ph.D. IDRE Fellow Department of Molecular, Cell, and Developmental Biology University of California Los Angeles Abstract: DNA methylation signatures have high predictive value and could be used to predict health outcomes. Challenges remained in clinical studies such as the large population variations and the biopsy with mixed cell types which all contribute to DNA methylat...
Introduction to Network Analysis Methodologies and Tools
มุมมอง 7225 หลายเดือนก่อน
Are you interested in the connections between people? Places? Concepts? Things? Do you want to visualize data in a way that is comprehensible to a human? Do you want to see how information flows through systems? Then network analysis is for you! This introductory workshop will introduce participants to network analysis, with an emphasis on its use for data-driven humanities research. Upon compl...
Digital Humanities and HPC
มุมมอง 665 หลายเดือนก่อน
In this presentation, we will explore how the HPC can be used to accomplish common DH tasks, such as network and GIS analysis with large data sets which would be computationally difficult or expensive on typical desktop / laptop hardware. We will use least-cost pathing with GDAL, network analysis with Python, and general DH data analysis and visualization with Jupyter Notebooks. This workshop i...
Contextualizing Collections: Intro to Immersive Annotated 360 Virtual Tours with Adobe Captivate
มุมมอง 1326 หลายเดือนก่อน
Most would agree that in terms of creating virtual experiences as part of research, more context is better. Contextual information allows for a bigger picture to be seen and can provide in situ understanding, despite being remote. With the proliferation of 360 cameras, creating immersive virtual tours has become more commonplace. Whether it is to document the layout of a hydroelectric power pla...
Data-driven prediction of vortex dynamics with hierarchical graph neural networks
มุมมอง 2826 หลายเดือนก่อน
Abstract: Forecasting the dynamics of fluid flows plays a crucial role in our understanding of processes such as the swimming of fish, turbulence on a plane, and hurricane formation. Unfortunately, simulating these systems can be prohibitively expensive even though we often know the equations of motion. Due to this high computational cost, major effort has gone toward developing reduced-order m...
Epidemic Model Guided Machine Learning for COVID-19 Forecasts
มุมมอง 27010 หลายเดือนก่อน
Epidemic Model Guided Machine Learning for COVID-19 Forecasts
Comprehensive Lexical Resource for English Using Bayesian Deep Learning and Missing Data Methodology
มุมมอง 8410 หลายเดือนก่อน
Comprehensive Lexical Resource for English Using Bayesian Deep Learning and Missing Data Methodology
ECR OpenScience workshop March 24, 2022 - part 1
มุมมอง 7710 หลายเดือนก่อน
ECR OpenScience workshop March 24, 2022 - part 1
Unsupervised Discovery of Ancestry Informative Markers and Genetic Admixture Proportions
มุมมอง 25310 หลายเดือนก่อน
Unsupervised Discovery of Ancestry Informative Markers and Genetic Admixture Proportions
High Performance Machine Learning Using Scikit-Learn
มุมมอง 28310 หลายเดือนก่อน
High Performance Machine Learning Using Scikit-Learn
Intro to Julia: A fast dynamic language for statistical computing and data science
มุมมอง 35610 หลายเดือนก่อน
Intro to Julia: A fast dynamic language for statistical computing and data science
Dynamic multivariate task fMRI analysis using Partial Least Squares in Matlab
มุมมอง 29111 หลายเดือนก่อน
Dynamic multivariate task fMRI analysis using Partial Least Squares in Matlab
Cloud computing workshops: Introduction (Part 3)
มุมมอง 94ปีที่แล้ว
Cloud computing workshops: Introduction (Part 3)
Cloud computing workshops: Introduction (Part 2)
มุมมอง 67ปีที่แล้ว
Cloud computing workshops: Introduction (Part 2)
Cloud computing workshops: Introduction (Part 1)
มุมมอง 179ปีที่แล้ว
Cloud computing workshops: Introduction (Part 1)
Package management using Anaconda3 (Part 2)
มุมมอง 62ปีที่แล้ว
Package management using Anaconda3 (Part 2)
Package management using Anaconda3 (Part 1)
มุมมอง 101ปีที่แล้ว
Package management using Anaconda3 (Part 1)
Panel discussion on Interdisciplinary Research and Collaboration - Oct 29, 2021
มุมมอง 55ปีที่แล้ว
Panel discussion on Interdisciplinary Research and Collaboration - Oct 29, 2021
In 2:03:19, he said "I am just showing you the real world", I died.
Thanks for the informative video. For time-varying Cox model (2:32:50), do we still need to check PH assumption for the time-varying covariate? Thanks!
Can you please suggest how to perform survival analysis for paired data for longitudinal studies.
Great explanation. Has anyone ever thought of using these ideas for a language model? It could have continuous learning built in, due to the Bayesian Approach.
Excellent. Do you have a video for latent variable means comparison please?
Thanks for your very educative talks. I found very helpful.
General comment Prof. , @9.07, the real part id the natural frequency and wi is the growth rate of the eigenvalue problem. Thats the general convention.
Excellent teaching, thank you very much
Provide simulation with macine learning matlab etc
The first half was really great as an introduction to the topic. The second half is absolutely useless. Filling your slides with formulas and switching back and forth between slides is no way to teach a topic.
Definitely, the best R tutorial I have ever come across on TH-cam! Good stuff!
100% This video is great
Thank you for such a detailed introduction to SEM. I have a question - at 46:18 the model is called a "saturated model" because the df = 0. However I have been reading that a "saturated model" occurs when there are the same number of parameters as there are data points. In this case, the model has 5 parameters and 500 data points. Is it still a saturated model then?
very insightful, I would wish to know how to use these commands after doing missing imputation with MICE
I have learned so much, gracias!
how do we get the value of the latent ? not the variance but the value
Thanks a lot! Greetings from University of Adelaide.
Fabulous Lecture
YOUR THE BEST, YOU JUST SIMPLIFIED EVERYTHING THANKYOU SO MUCH PROFESSOR
great video! Thanks. What do you think of using the estimation method DWLS instead of ML for ordinal items (such as those in the video "strongly disagree to strongly agree")? I have just read a paper (Reimann et al. 2024) where they used DWLS in a 2-factor CFA and got a great RMSEA (0.01). Their rationale was that the responses are ordinal and not continuous. Interestingly, I could run the same data set with ML and got an RMSEA = 0.13. Obviously a big difference. In papers, authors often do not even mention their estimation method.
Wow, this is outstanding! Will it be possible to do similar in R program
Wow..what a tutorial Thank you so much❤❤
For a complete novice to Mplus this was a great introductory tutorial. Thank you.
I am in an intermediate statistics and research course for my doctoral program. I began reading Hayes and found myself dissociating with glazed stares. This workshop has provided an informative path to at least begin to consume the material with some understanding. Your assistance with downloading the PROCESS macro was also very helpful. I hope to find moderation and conditional process analysis workshops from this source as well. Thank you very much!!
Matlab? Mathematica? Maple? Python? R? Thanks.
Once I save the folium html, after two days, the interactive visualization stops to display. What could be the problem?
Thank you so much. Very helpful!
Great video thank you!
Thanks for the great tutorial. At 1:51:35, is the wt.loss also by the time of beginning the study (treatment), like the age variable? Thanks.
My rmse is more than 0.8
My cfi is 1 and rmse NA
Thank you very much for an excellent lecture on CFA. Just a small comment/correction on the very final exercise: the Test statistic for the User Model, is 554.191. In your solution, it is 562.790. and the Degree of Freedom is 20, not 21. By putting these numbers in the formula, we get the correct CFI, which is 0.871 (rounded).
The 'li' syntax didn't work for me. It returned errors
Still can't believe this is free to watch for everyone. Thank you so much.
So much rambling in this presentation. The content gets lost in it.
Great video! Great delivery and insights!
This is the resource I needed for my Dissertation. As someone with no strong stat and R background, this really helped me. Thank you very much Dr. Lin!
I swear to god, this is the least technical intro I've ever seen in a stat course. It speaks volumes of the teachin style. Amazing job.
this is so bad!
this is the worst tutorial ever, this person cannot even speak English properly. why UCLA does not ask someone to teach this material who can actually speak English? waste of resources and time!
Hello, Author. Could you tell me how to get the residual vairances of a MSE by lavaan()? Thanks
The HR for wt.loss in the lung data has a p value in excess of 0.05. Thus it is not statistically significant.
I am not really seeing the difference between informative and formative censoring. I am also struggling with the comparison with NAs. NAs missing at random is easy to spot but not so sure about the censoring.
This is a very informative presentation and clearly laid out. However, in terms of earthquakes I don't think it is safe to say that the hazard is constant. Hazard along the San Andreas fault should clearly vary depending on the region next to the fault (rock types vary, last time there was earthquake and so on).
Excellent , thanks for sharing -- Best Regards
Great workshop, Can I found any advance level course of the instructor?
very good analysis. well done
Animated plots from 1:01:40
Recipes start at 47:52
Dr. Lin, is there any video on your seminar on EFA?
These videos are fantastic. Thank you!