How Two University Students are Building an AI Chat Bot Using TensorFlow and oneAPI

Parallel programming models are often used on large scale systems, with huge datasets and a large amount of obvious parallelism. In this podcast, Tony talks to two university students that are building a chat bot using consumer hardware and standard frameworks like TensorFlow and oneAPI. They use TensorFlow to enable their AI model and SYCL to optimize various parts of their data pipeline.

They also talk about the Intel Student Ambassador program, Intel Discord, and how Josh and Harvey became part of the Intel social community.

For more information see:
Gavin AI Chat Bot
github.com/Gavin-Development

TensorFlow
tensorflow.org

SYCL
sycl.tech

oneAPI
oneapi.io
intel.com/content/www/us/en/developer/tools/oneapi/overview.html

Building LLVM to compile SYCL for NVIDIA GPUs
intel.github.io/llvm-docs/GetStartedGuide.html#build-dpc-toolchain-with-support-for-nvidia-cuda

Intel Student Ambassador Program
intel.com/content/www/us/en/developer/community/ambassadors.html

Intel Discord
discord.com/invite/intel

OpenAI – GPT-2, GPT-3 resources
openai.com

Google LaMDA
blog.google/technology/ai/lamda

Kaggle
kaggle.com

AI Predicts Heart Disease Risk Using Single X-Ray
press.rsna.org/timssnet/media/pressreleases/14_pr_target.cfm?ID=2388

Guests
Joshua Shiells – Student @ University of Kent
Harvey Johnson – Student @ University of Nottingham