This Week in Machine Learning & AI-logo

This Week in Machine Learning & AI

Technology Podcasts >

More Information


United States






Productive Machine Learning at LinkedIn with Bee-Chung Chen - TWiML Talk #200

In this episode of our AI Platforms series, we’re joined by Bee-Chung Chen, Principal Staff Engineer and Applied Researcher at LinkedIn. Bee-Chung and I caught up to discuss LinkedIn’s internal AI automation platform, Pro-ML, which was built with the hopes of providing a single platform for the entire lifecycle of developing, training, deploying, and testing machine learning models. In our conversation, Bee-Chung details Pro-ML, breaking down some of the major pieces of the pipeline...


Scaling Deep Learning on Kubernetes at OpenAI with Christopher Berner - TWiML Talk #199

In this episode of our AI Platforms series we’re joined by OpenAI’s Head of Infrastructure, Christopher Berner. Chris has played a key role in overhauling OpenAI’s deep learning infrastructure of the course of his two years with the company. In our conversation, we discuss the evolution of OpenAI’s deep learning platform, the core principles which have guided that evolution, and its current architecture. We dig deep into their use of Kubernetes and discuss various ecosystem players and...


Bighead: Airbnb's Machine Learning Platform with Atul Kale - TWiML Talk #198

In this episode of our AI Platforms series, we’re joined by Atul Kale, Engineering Manager on the machine learning infrastructure team at Airbnb. Atul and I met at the Strata Data conference a while back to discuss Airbnb’s internal machine learning platform, Bighead. In our conversation, Atul outlines the ML lifecycle at Airbnb and how the various components of Bighead support it. We then dig into the major components of Bighead, which include Redspot, their supercharged Jupyter notebook...


Facebook's FBLearner Platform with Aditya Kalro - TWiML Talk #197

In this, the kickoff episode of our AI Platforms series, we’re joined by Aditya Kalro, Engineering Manager at Facebook, to discuss their internal machine learning platform FBLearner Flow. Introduced in May of 2016, FBLearner Flow is the workflow management platform at the heart of the Facebook ML engineering ecosystem. In our conversation, Aditya and I discuss the history and development of the platform, as well as its functionality and its evolution from an initial focus on model...


Geometric Statistics in Machine Learning w/ geomstats with Nina Miolane - TWiML Talk #196

In this episode we’re joined by Nina Miolane, researcher and lecturer at Stanford University. Nina and I recently spoke about her work in the field of geometric statistics in machine learning. Specifically, we discuss the application of Riemannian geometry, which is the study of curved surfaces, to ML. Riemannian geometry can be helpful in building machine learning models in a number of situations including in computational anatomy and medicine where it helps Nina create models of organs...


Milestones in Neural Natural Language Processing with Sebastian Ruder - TWiML Talk #195

In this episode, we’re joined by Sebastian Ruder, a PhD student studying natural language processing at the National University of Ireland and a Research Scientist at text analysis startup Aylien. In our conversation, Sebastian and I discuss recent milestones in neural NLP, including multi-task learning and pretrained language models. We also discuss the use of attention-based models, Tree RNNs and LSTMs, and memory-based networks. Finally, Sebastian walks us through his recent ULMFit...


Natural Language Processing at StockTwits with Garrett Hoffman - TWiML Talk #194

In this episode, we’re joined by Garrett Hoffman, Director of Data Science at Stocktwits. Garrett and I caught up at last month’s Strata Data conference, where he presented a tutorial on “Deep Learning Methods for NLP with Emphasis on Financial Services.” Stocktwits is a social network for the investing community which has its roots in the use of the $cashtag on Twitter. In our conversation, we discuss applications such as Stocktwits’ own use of “social sentiment graphs” built on...


Advanced Reinforcement Learning & Data Science for Social Impact with Vukosi Marivate - TWiML Talk #193

In this, the final show of our Deep Learning Indaba Series, we speak with Vukosi Marivate, Chair of Data Science at the University of Pretoria and a co-organizer of the Indaba. My conversation with Vukosi fell into two distinct parts. The first part focused on his PhD research in the area of reinforcement learning, discussing several advanced RL scenarios including inverse RL, multiple agent RL, and using RL when we have incomplete knowledge of the environment. We then moved on to discuss...


AI Ethics, Strategic Decisioning and Game Theory with Osonde Osoba - TWiML Talk #192

In this episode of our Deep Learning Indaba Series, we’re joined by Osonde Osoba, Engineer at RAND Corporation and Professor at the Pardee RAND Graduate School. Osonde and I spoke on the heels of the Indaba, where he presented on AI Ethics and Policy. We discuss his framework-based approach for evaluating ethical issues, such as applying the ethical principles laid out in the Belmont Report, and how to build an intuition for where ethical flashpoints may exist in these discussions. We...


Acoustic Word Embeddings for Low Resource Speech Processing with Herman Kamper - TWiML Talk #191

In this episode of our Deep Learning Indaba Series, we’re joined by Herman Kamper, Lecturer in the electrical and electronics engineering department at Stellenbosch University in SA and a co-organizer of the Indaba. Herman and I discuss his work on limited- and zero-resource speech recognition, how those differ from regular speech recognition, and the tension between linguistic and statistical methods in this space. We dive into the specifics of the methods being used and developed in...


Learning Representations for Visual Search with Naila Murray - TWiML Talk #190

In this episode of our Deep Learning Indaba series, we’re joined by Naila Murray, Senior Research Scientist and Group Lead in the computer vision group at Naver Labs Europe. Naila presented at the Indaba on computer vision, and in this discussion we explore her work on visual attention, including why visual attention is important and the trajectory of work in the field over time. We also discuss her paper “Generalized Max Pooling,” and her recent research interest in learning...


Evaluating Model Explainability Methods with Sara Hooker - TWiML Talk #189

In this, the first episode of the Deep Learning Indaba series, we’re joined by Sara Hooker, AI Resident at Google Brain. I had the pleasure of speaking with Sara in the run-up to the Indaba about her work on interpretability in deep neural networks. We discuss what interpretability means and when it’s important, and explore some nuances like the distinction between interpreting model decisions vs model function. We also dig into her paper Evaluating Feature Importance Estimates and look...


Graph Analytic Systems with Zachary Hanif - TWiML Talk #188

In this, the final episode of our Strata Data Conference series, we’re joined by Zachary Hanif, Director of Machine Learning at Capital One’s Center for Machine Learning. Zach led a session at Strata called “Network effects: Working with modern graph analytic systems,” which we had a great chat about back in New York. We start our discussion with a look at the role of graph analytics in the machine learning toolkit, including some important application areas for graph-based systems. We...


Diversification in Recommender Systems with Ahsan Ashraf - TWiML Talk #187

In this episode of our Strata Data conference series, we’re joined by Ahsan Ashraf, data scientist at Pinterest. In our conversation, Ahsan and I discuss his presentation from the conference, “Diversification in recommender systems: Using topical variety to increase user satisfaction.” We cover the experiments his team ran to explore the impact of diversification in user’s boards, the methodology his team used to incorporate variety into the Pinterest recommendation system, the metrics they...


The Fastai v1 Deep Learning Framework with Jeremy Howard - TWiML Talk #186

In today's episode we’ll be taking a break from our Strata Data conference series and presenting a special conversation with Jeremy Howard, founder and researcher at is a company many of our listeners are quite familiar with due to their popular deep learning course. This episode is being released today in conjunction with the company’s announcement of version 1.0 of their fastai library at the inaugural Pytorch Devcon in San Francisco. Jeremy and I cover a ton of ground...


Federated ML for Edge Applications with Justin Norman - TWiML Talk #185

In this episode of our Strata Data conference series, we’re joined by Justin Norman, Director of Research and Data Science Services at Cloudera Fast Forward Labs. Fast Forward Labs was an Applied AI research firm and consultancy founded by Hilary Mason, who’s TWiML Talk episode remains an all-time fan favorite. My chat with Justin took place on the 1 year anniversary of Fast Forward Labs’ acquisition by Cloudera, so we start with an update on the company before diving into a look at some of...


Exploring Dark Energy & Star Formation w/ ML with Viviana Acquaviva - TWiML Talk #184

In today’s episode of our Strata Data series, we’re joined by Viviana Acquaviva, Associate Professor at City Tech, the New York City College of Technology. Viviana led a tutorial at the conference, titled “Learning Machine Learning using Astronomy data sets.” In our conversation, we begin by discussing an ongoing project she’s a part of called the “Hobby-Eberly Telescope Dark Energy eXperiment,” or HETDEX. In this project, Viviana tackles the challenge of understanding of how and why the...


Document Vectors in the Wild with James Dreiss - TWiML Talk #183

In this episode of our Strata Data series we’re joined by James Dreiss, Senior Data Scientist at international news syndicate Reuters. James and I sat down to discuss his talk from the conference “Document vectors in the wild, building a content recommendation system,” in which he details how Reuters implemented document vectors to recommend content to users of their new “infinite scroll” page layout. In our conversation we take a look at what document vectors are and how they’re created,...


Applied Machine Learning for Publishers with Naveed Ahmad - TWiML Talk #182

In today’s episode we’re joined by Naveed Ahmad, Senior Director of data engineering and machine learning at Hearst Newspapers. A few months ago, Naveed gave a talk at the Google Cloud Next Conference on “How Publishers Can Take Advantage of Machine Learning.” In our conversation, we discuss into the role of ML at Hearst, including their motivations for implementing it and some of their early projects, the challenges of data acquisition within a large organization, and the benefits they...


Anticipating Superintelligence with Nick Bostrom - TWiML Talk #181

In this episode, we’re joined by Nick Bostrom, professor in the faculty of philosophy at the University of Oxford, where he also heads the Future of Humanity Institute, a multidisciplinary institute focused on answering big-picture questions for humanity with regards to AI safety and ethics. Nick is of course also author of the book “Superintelligence: Paths, Dangers, Strategies.” In our conversation, we discuss the risks associated with Artificial General Intelligence and the more advanced...