<turbo-stream action="append" target="audio_clips_list"><template>
    <hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308690-interdisciplinary-data-and-helping-humans-be-creative"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Interdisciplinary Data and Helping Humans Be Creative 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In Episode 10 we talk with David Blei of Columbia University. We talk about his work on latent dirichlet allocation, topic models, the PhD program in data that he’s helping to create at Columbia and why exploring data is inherently multidisciplinary. We learn about Markov Chain Monte Carlo and take a listener question about how machine learning can make humans more creative.
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
34m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1431016374" data-format="short_date">May 07, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
34m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308692-starting-simple-and-machine-learning-in-meds"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Starting Simple and Machine Learning in Meds 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In episode nine we talk with George Dahl, of  the University of Toronto, about his work on the Merck molecular activity challenge on kaggle and speech recognition. George recently successfully defended his thesis at the end of March 2015. (Congrats George!) We learn about how networks and graphs can help us understand latent properties of relationships, and we take a listener question about jus...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
38m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1429799518" data-format="short_date">Apr 23, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
38m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308694-spinning-programming-plates-and-creative-algorithms"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Spinning Programming Plates and Creative Algorithms
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
On episode eight we talk with Charles Sutton, a professor in the School of Informatics University of Edinburgh about computer programming and using machine learning how to better understand how it’s done well. Ryan introduces us to collaborative filtering, a process that helps to make predictions about taste. Netflix and Amazon use it to recommend movies and items. It&#39;s the process that the Net...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
35m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1428578327" data-format="short_date">Apr 09, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
35m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308695-the-automatic-statistician-and-electrified-meat"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
The Automatic Statistician and Electrified Meat
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In episode seven of Talking Machines we talk with Zoubin Ghahramani, professor of Information Engineering in the Department of Engineering at the University of Cambridge. His project, The Automatic Statistician, aims to use machine learning to take raw data and give you statistical reports and natural languages summaries of what trends that data shows. We get really hungry exploring Bayesian No...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
46m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1427379303" data-format="short_date">Mar 26, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
46m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308697-the-future-of-machine-learning-from-the-inside-out"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
The Future of Machine Learning from the Inside Out 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
We hear the second part of our conversation with with Geoffrey Hinton (Google and University of Toronto), Yoshua Bengio (University of Montreal) and Yann LeCun (Facebook and NYU). They talk with us about this history (and future) of research on neural nets. We explore how to use Determinantal Point Processes. Alex Kulesza  and Ben Taskar (who passed away recently) have done some really exciting...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
28m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1426285011" data-format="short_date">Mar 13, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
28m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308698-the-history-of-machine-learning-from-the-inside-out"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
The History of Machine Learning from the Inside Out 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In episode five of Talking Machines, we hear the first part of our conversation with Geoffrey Hinton (Google and University of Toronto), Yoshua Bengio (University of Montreal) and Yann LeCun (Facebook and NYU). Ryan introduces us to the ideas in tensor factorization methods for learning latent variable models (which is both a tongue twister and and one of the new tools in ML). To find out more ...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
33m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1424967861" data-format="short_date">Feb 26, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
33m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308700-using-models-in-the-wild-and-women-in-machine-learning"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Using Models in the Wild and Women in Machine Learning 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In episode four we talk with Hanna Wallach, of Microsoft Research. She&#39;s also a professor in the Department of Computer Science, University of Massachusetts Amherst and one of the founders of Women in Machine Learning (better known as WiML). We take a listener question about scalability and the size of data sets. And Ryan takes us through topic modeling using Latent Dirichlet allocation (say th...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
45m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1423755605" data-format="short_date">Feb 12, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
45m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308701-common-sense-problems-and-learning-about-machine-learning"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Common Sense Problems and Learning about Machine Learning
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
On episode three of Talking Machines we sit down with Kevin Murphy who is currently a research scientist at Google. We talk with him about the work he’s doing there on the Knowledge Vault, his textbook, Machine Learning: A Probabilistic Perspective (and its arch nemesis which we won’t link to), and how to learn about machine learning (Metacademy is a great place to start). We tackle a listener ...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
41m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1422541571" data-format="short_date">Jan 29, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
41m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308703-machine-learning-and-magical-thinking"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Machine Learning and Magical Thinking 
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
Today on Talking Machines we hear from Google researcher Ilya Sutskever about his work, how he became interested in machine learning, and why it takes a little bit of magical thinking. We take your questions, and explore where the line between human programming and computer learning actually is. And we sift through some news from the field, Ryan explains the concepts behind one of the best pape...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
35m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1421329958" data-format="short_date">Jan 15, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
35m
</div>
</div>
</div>
</a></div>
<hr class="mvn mhs text-black-50 opacity-25">
<div class="card rounded-0 border-0 pas qa-audio-clip-overview" style="--bs-card-bg: transparent;">
<a class="text-decoration-none" href="/posts/3308704-hello-world"><div class="Episode-list-grid card-body pan">
<div class="l-flex align-items-baseline gap-2 gap-md-3">
<img srcset="https://audioboom.com/i/15246144/75x75/c 75w, https://audioboom.com/i/15246144/150x150/c 150w, https://audioboom.com/i/15246144/300x300/c 300w, https://audioboom.com/i/15246144/600x600/c 600w, https://audioboom.com/i/15246144/1400x1400/c 1400w" sizes="(max-width: 400px) 64px, 96px" style="background-color: #ffffff; max-width: 96px; width: 15cqw;" class="js-img-bg ratio-square rounded-1" loading="lazy" src="https://audioboom.com/i/15246144/1400x1400/c" />
<div class="vstack gap-1 my-auto">
<h5 class="text-line-clamp text-line-clamp-3 balanced-h fs-6 fs-5-lg fw-normal mb-0">
Hello World!
</h5>
<div class="text-line-clamp text-line-clamp-3 balanced-p fs-8 text-muted text-break">
In the first episode of Talking Machines we meet our hosts, Katherine Gorman (nerd, journalist) and Ryan Adams (nerd, Harvard computer science professor), and explore some of the interviews you&#39;ll be able to hear this season. Today we hear some short clips on big issues, we&#39;ll get technical, but today is all about introductions.We start with Kevin Murphy of Google talking about his textbook tha...
</div>
<div class="text-muted df align-items-baseline gap-2 fs-8">
<span class="numeric-tabular d-sm-none">
41m
</span>
<span class="d-sm-none">
&bull;
</span>
<span><span class="js-time" data-epochtime="1420135754" data-format="short_date">Jan 01, 2015</span></span>
</div>
</div>
</div>
<div class="d-none d-sm-grid" style="justify-self: center; align-items: center;">
<div class="fs-8 numeric-tabular text-nowrap text-muted phs">
41m
</div>
</div>
</div>
</a></div>

</template></turbo-stream>
  <turbo-stream action="remove" target="audio_clips_pagination"></turbo-stream>
