https://datasciencela.github.io/tag/gpu/Recent content in GPU on DataScience.LAHugo -- gohugo.ioen-usDataScience.LA, 2014–2021 · Read-only archive: comments are closed.Thu, 13 Oct 2022 00:02:42 -0700https://datasciencela.github.io/deep-learning-whisper/Tue, 03 May 2016 11:37:29 -0700https://datasciencela.github.io/deep-learning-whisper/<p><strong>Deep Learning @Whisper</strong><br> <strong>talk by Nick Stucky-Mack</strong></p> <p>Video now available, thank you to community member Carl Mullins for providing video services:</p> <figure class="yt-lite" data-id="VDV8GzkftIc"> <a class="yt-lite-btn" href="https://www.youtube.com/watch?v=VDV8GzkftIc" title="Play: Deep Learning @Whisper THU, MAY 12 AT 6 00 PM, VENICE, CA"> <img src="https://i.ytimg.com/vi/VDV8GzkftIc/hqdefault.jpg" alt="Deep Learning @Whisper THU, MAY 12 AT 6 00 PM, VENICE, CA" loading="lazy" width="480" height="360"> <span class="yt-lite-play" aria-hidden="true"></span> </a> <figcaption>▶ Deep Learning @Whisper THU, MAY 12 AT 6 00 PM, VENICE, CA</figcaption> </figure> <script> document.addEventListener('click', function (e) { var a = e.target.closest('.yt-lite-btn'); if (!a) return; e.preventDefault(); var f = a.parentNode, s = f.dataset.start, i = document.createElement('iframe'); i.src = 'https://www.youtube-nocookie.com/embed/' + f.dataset.id + '?autoplay=1' + (s ? '&start=' + s : ''); i.title = a.title; i.allowFullscreen = true; i.allow = 'accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture'; a.replaceWith(i); }); </script> <p>In this talk we will discuss how Whisper uses machine learning for natural  language processing tasks. We will focus on how Whisper applies deep learning to moderate content created by its more than 20 million monthly active users. The talk will explore the problem of short text classification, and will cover Whisper&rsquo;s choices in machine learning models, software development, and hardware.</p>