Deep learning neural networks have become a prominent tool in science and machine learning. This webinar will provide a brief overview of the main concepts of neural networks and feature discovery. We will also demonstrate the basic convolution neural network for digit recognition using TensorFlow and try to get an intuition about how the network performs and what defines deep learning in practice. We will also review some useful notes on running deep networks on HPCs, such as using tensorboard, notebooks, and batch jobs. 

A live tutorial on machine learning and deep learning framework using TensorFlow, Keras and Scikit-Learn.

As the volume of data generated continues to explode, the need to move data quickly and reliably for analysis, collaboration, and storage increases. Whether you want to move data off expensive instruments, sync data between local and remote resources, publish data to portals, or even archive data for long-term preservation, automating the data handling will reduce obstacles and make the data available to others more quickly. In this webinar you will learn some best practices and automation techniques. Learn how to:

This live webinar is targeted toward researchers with the largest-scale computational, analysis, and storage needs. Join the ACCESS Allocations team on Tuesday, April 4 @ 3PM ET, as they detail the required components, review criteria, and other necessary information to craft a successful request.

Requests are due on April 15 and successful requests will begin or renew on July 1. For more information on "Maximize" requests, please see the website.

OSC Workshop Series with NVIDIA & ACCESS

The Ohio Supercomputer Center (OSC) in collaboration with NVIDIA and ACCESS will host the Four Ways to GPU Computing Workshop on Monday, April 3, 2023 from 2:00 p.m. to 3:00 p.m. EST.

Four Ways to GPU Computing

With Globus sharing you can easily reduce storage costs and employ a “self-service” method for researchers to access and share data. With over 40,000 Globus-enabled systems, many researchers are already using Globus to store and share data. Come learn how to deploy guest collections and hear directly from an ACCESS resource provider how Globus eliminates some of the mundane time-consuming and hand-holding tasks involved in sharing research data securely and reliably.

In this webinar you will learn:

· How to search and find other Globus collections or endpoints

This short course covers a brief introduction to RNA-seq technology, NGS QC, and differential expression analysis/data visualization.

More information about this short course at https://hprc.tamu.edu/training/aces_rnaseq.html

This bioinformatics workshop will introduce the containerized bioinformatics computing resources provided by Purdue Rosen Center for Advanced Computing in ACCESS Anvil. Familiarity with the Linux/Unix command-line is recommended.

Topics overview:

• Containerized bioinformatics applications on Anvil
• Open OnDemand for GUI applications
• Customized R containers for RNAseq and scRNAseq analysis
• Customized Python containers supporting Jupyter
• Batch jobs and interactive jobs

Learn how to get started with Globus. See how easy it is to get your data to and from ACCESS resources (a few megabytes to tens of terabytes at a time) and why over 1,600 campuses and research organizations offer Globus services for managing research data. Learn how to move data between your campus and ACCESS systems, how to schedule recurring transfers and synchronization tasks, and how to share your data on an ACCESS system with your collaborators at multiple institutions.

This short course covers basic topics in numerical computation and scientific programming using the Julia programming language. Topics include basic language elements and concepts, programming best practice, and relevant open source tools. This is a basic to intermediate level course.

More information about this short course at https://hprc.tamu.edu/training/aces_julia.html

This short course introduces concepts of metagenomics analysis based on data generated by Next Generation Sequencing (NGS) technology.

More information about this short course at https://hprc.tamu.edu/training/aces_metagenomics.html

Managing data efficiently on a supercomputer is very important from both the users' and system's perspectives. Users need to be aware of various data storage and management mechanisms, in addition to their impact on application and system performance. In this webinar, we will cover a few basic data management techniques and I/O best practices in the context of the Expanse system at SDSC. We will learn about the file systems that are part of Expanse and discuss the pros and cons of using these file systems in terms of I/O performance, storage capacity, shared access, and backup.

Many times, researchers couldn't convert their research models into Software Applications. This is the place where RevFrame comes into the Picture. In this Short Course, you get to know how to use RevFrame, a Framework that is designed to assist ML/AI/NLP researchers to effortlessly convert their models into web applications. This is a basic to intermediate-level course.

The Pittsburgh Supercomputing Center is pleased to present a Machine Learning and Big Data workshop, sponsored by ACCESS. 

This workshop will focus on topics including big data analytics and machine learning with Spark, and deep learning using Tensorflow.

This will be an IN PERSON event hosted by various satellite sites, there WILL NOT be a direct to desktop option for this event.  The satellite site list(subject to change) is as follows:

This short course is an introduction to Clara Parabricks, a software suite that allows users to perform secondary analysis of next generation sequencing DNA and RNA data. The software incorporated into Clara Parabricks has been optimized to run on GPUs, drastically increasing the speed at which common NGS analyses and tasks can be completed.

More information about this Short Course https://hprc.tamu.edu/training/aces_parabrick.html

This short course covers basic to intermediate level topics with live illustrations and hands-on exercises using the Jupyter notebook web application.

The Neocortex team is pleased to announce the Neocortex Spring 2023 Call for Proposals (NeocortexSpring2023CFP). Neocortex is an NSF-funded supercomputer that features Cerebras accelerators and an HPE Superdome Flex server designed to radically speed up AI and HPC research. The mission of Neocortex is to characterize the strengths and limitations of these promising hardware technologies.

This short course covers basic topics in CUDA programming on NVIDIA GPUs. Topics include

• CUDA architecture
• basic language usage of CUDA C/C++
• writing, executing CUDA code.

More information about this Short Course https://hprc.tamu.edu/training/intro_cuda.html

This webinar covers the basics of connecting to Anvil, managing the user environment, running jobs, and data management. Knowledge of basic UNIX commands and submitting batch jobs to a cluster will be helpful.

Topics Overview:

• Anvil system architecture including node types, storage, interconnects, and networking.
• Getting started with accounts and allocations
• Compilation and programming environment on Anvil
• Running Jobs on Anvil
• Data management and transfer on Anvil
• Q&A