284
  • Doctor AI - Duration: 41 minutes.

    • 3 days ago
    • 23 views
    hen faced with medical issues, would you want to be seen by a human or a machine? In this episode, guest Edward Choi, co-author of the study titled Doctor AI: Predicting Clinical Events via Recurre...
  • Two Minute Papers - Channel

    • 232 videos
    Awesome research for everyone with two new science videos every week. You'll love it!

    Our links:
    Web → https://cg.tuwien.ac.at/~zsolnai/
    Patreon → https://www.patreon.com/TwoMinutePapers
    Facebook → h
    • CHANNEL
    55,450
  • DeepLearning.TV - Channel

    • 31 videos
    DeepLearning.TV is all about Deep Learning, the field of study that teaches machines to perceive the world. Starting with a series that simplifies Deep Learning, the channel features topics such as Ho
    • CHANNEL
    41,199
  • Activation Functions - Duration: 14 minutes.

    • 1 week ago
    • 35 views
    In a neural network, the output value of a neuron is almost always transformed in some way using a function. A trivial choice would be a linear transformation which can only scale the data. However...
  • MS Build 2017 - Duration: 27 minutes.

    • 2 weeks ago
    • 19 views
    This episode recaps the Microsoft Build Conference.  Kyle recently attended and shares some thoughts on cloud, databases, cognitive services, and artificial intelligence.  The episode inc...
  • [MINI] Max-pooling - Duration: 12 minutes.

    • 3 weeks ago
    • 34 views
    Max-pooling is a procedure in a neural network which has several benefits. It performs dimensionality reduction by taking a collection of neurons and reducing them to a single value for future laye...
  • Carl Mullins - Channel

    • 151 videos
    • CHANNEL
    361
  • Unsupervised Depth Perception - Duration: 23 minutes.

    • 1 month ago
    • 33 views
    This episode is an interview with Tinghui Zhou.  In the recent paper "Unsupervised Learning of Depth and Ego-motion from Video", Tinghui and collaborators propose a deep learning architecture ...
  • [MINI] Convolutional Neural Networks - Duration: 14 minutes.

    • 1 month ago
    • 44 views
    CNNs are characterized by their use of a group of neurons typically referred to as a filter or kernel.  In image recognition, this kernel is repeated over the entire image.  In this way, ...
  • Mutli-Agent Diverse Generative Adversarial Networks - Duration: 29 minutes.

    • 1 month ago
    • 42 views
    Despite the success of GANs in imaging, one of its major drawbacks is the problem of 'mode collapse,' where the generator learns to produce samples with extremely low variety.

    To address this i...
  • Mark Woodward - Channel

    • 14 videos
    • CHANNEL
    34
  • James Costa - Channel

    • 11 videos
    • CHANNEL
    25
  • Predictive Policing - Duration: 36 minutes.

    • 1 month ago
    • 29 views
    Kristian Lum (@KLdivergence) joins me this week to discuss her work at @hrdag on predictive policing. We also discuss Multiple Systems Estimation, a technique for inferring statistical informa...
  • [MINI] Leakage - Duration: 12 minutes.

    • 1 month ago
    • 16 views
    If you'd like to make a good prediction, your best bet is to invent a time machine, visit the future, observe the value, and return to the past. For those without access to time travel technology, ...
  • Trusting Machine Learning Models with LIME - Duration: 35 minutes.

    • 1 month ago
    • 54 views
    Machine learning models are often criticized for being black boxes. If a human cannot determine why the model arrives at the decision it made, there's good cause for skepticism. Classic inspection ...
  • [MINI] Goodhart's Law - Duration: 10 minutes.

    • 1 month ago
    • 39 views
    Goodhart's law states that "When a measure becomes a target, it ceases to be a good measure". In this mini-episode we discuss how this affects SEO, call centers, and Scrum.
  • Studying Competition and Gender Through Chess - Duration: 34 minutes.

    • 1 month ago
    • 10 views
    Prior work has shown that people's response to competition is in part predicted by their gender. Understanding why and when this occurs is important in areas such as labor market outcomes. A well s...
  • The Police Data and the Data Driven Justice Initiatives - Duration: 49 minutes.

    • 1 month ago
    • 11 views
    In this episode I speak with Clarence Wardell and Kelly Jin about their mutual service as part of the White House's Police Data Initiative and Data Driven Justice Initiative respectively.

    The P...
  • Music21 - Duration: 34 minutes.

    • 1 month ago
    • 7 views
    Our guest today is Michael Cuthbert, an associate professor of music at MIT and principal investigator of the Music21 project, which we focus our discussion on today.

    Music21 is a python librar...
  • [MINI] Paxos - Duration: 14 minutes.

    • 1 month ago
    • 5 views
    Paxos is a protocol for arriving a consensus in a distributed computing system which accounts for unreliability of the nodes.  We discuss how this might be used in the real world in the event ...
  • MS Connect Conference - Duration: 42 minutes.

    • 1 month ago
    • 1 view
    Cloud services are now ubiquitous in data science and more broadly in technology as well. This week, I speak to Mark Souza, Tobias Ternström, and Corey Sanders about various aspects of data at scal...
  • [MINI] Receiver Operating Characteristic (ROC) Curve - Duration: 11 minutes.

    • 1 month ago
    • 24 views
    An ROC curve is a plot that compares the trade off of true positives and false positives of a binary classifier under different thresholds. The area under the curve (AUC) is useful in determining h...
  • [MINI] Calculating Feature Importance - Duration: 13 minutes.

    • 1 month ago
    • 32 views
    For machine learning models created with the random forest algorithm, there is no obvious diagnostic to inform you which features are more important in the output of the model. Some straightforward...
  • Election Predictions - Duration: 21 minutes.

    • 1 month ago
    • 3 views
    Jo Hardin joins us this week to discuss the ASA's Election Prediction Contest. This is a competition aimed at forecasting the results of the upcoming US presidential election competition. More deta...
  • Multiple Comparisons and Conversion Optimization - Duration: 30 minutes.

    • 1 month ago
    • 6 views
    I'm joined by Chris Stucchio this week to discuss how deliberate or uninformed statistical practitioners can derive spurious and arbitrary results via multiple comparisons. We discuss p-hacking and...
  • Data Science at eHarmony - Duration: 42 minutes.

    • 1 month ago
    • 18 views
    I'm joined this week by Jon Morra, director of data science at eHarmony to discuss a variety of ways in which machine learning and data science are being applied to help connect people for successf...
  • Stealing Models from the Cloud - Duration: 37 minutes.

    • 1 month ago
    • 4 views
    Platform as a service is a growing trend in data science where services like fraud analysis and face detection can be provided via APIs. Such services turn the actual model into a black box to the ...
  • The Library Problem - Duration: 35 minutes.

    • 1 month ago
    • 13 views
    We close out 2016 with a discussion of a basic interview question which might get asked when applying for a data science job. Specifically, how a library might build a model to predict if a book wi...
  • Machine Learning on Images with Noisy Human-centric Labels - Duration: 23 minutes.

    • 1 month ago
    • 8 views
    When humans describe images, they have a reporting bias, in that the report only what they consider important. Thus, in addition to considering whether something is present in an image, one should ...
  • 2016 Holiday Special - Duration: 39 minutes.

    • 1 month ago
    • 2 views
    Today's episode is a reading of Isaac Asimov's Franchise.  As mentioned on the show, this is just a work of fiction to be enjoyed and not in any way some obfuscated political statement. ...
  • Causal Impact - Duration: 34 minutes.

    • 1 month ago
    • 15 views
    Today's episode is all about Causal Impact, a technique for estimating the impact of a particular event on a time series. We talk to William Martin about his research into the impact releases have ...
  • [MINI] F1 Score - Duration: 9 minutes, 3 seconds.

    • 1 month ago
    • 1 view
    The F1 score is a model diagnostic that combines precision and recall to provide a singular evaluation for model comparison.  In this episode we discuss how it applies to selecting an interior...
  • [MINI] Entropy - Duration: 16 minutes.

    • 1 month ago
    • 1 view
    Classically, entropy is a measure of disorder in a system. From a statistical perspective, it is more useful to say it's a measure of the unpredictability of the system. In this episode we discuss ...
  • Predictive Models on Random Data - Duration: 36 minutes.

    • 1 month ago
    • 3 views
    This week is an insightful discussion with Claudia Perlich about some situations in machine learning where models can be built, perhaps by well-intentioned practitioners, to appear to be highly pre...
  • Detecting Terrorists with Facial Recognition? - Duration: 33 minutes.

    • 1 month ago
    • 8 views
    A startup is claiming that they can detect terrorists purely through facial recognition. In this solo episode, Kyle explores the plausibility of these claims.
  • Unstructured Data for Finance - Duration: 33 minutes.

    • 1 month ago
    • 15 views
    Financial analysis techniques for studying numeric, well structured data are very mature. While using unstructured data in finance is not necessarily a new idea, the area is still very greenfield. ...
  • [MINI] The CAP Theorem - Duration: 10 minutes.

    • 1 month ago
    • 12 views
    Distributed computing cannot guarantee consistency, accuracy, and partition tolerance. Most system architects need to think carefully about how they should appropriately balance the needs of their ...
  • Urban Congestion - Duration: 35 minutes.

    • 1 month ago
    • 5 views
    Urban congestion effects every person living in a city of any reasonable size. Lewis Lehe joins us in this episode to share his work on downtown congestion pricing. We explore topics of how differe...
  • [MINI] ANOVA - Duration: 12 minutes.

    • 1 month ago
    • 8 views
    Analysis of variance is a method used to evaluate differences between the two or more groups.  It works by breaking down the total variance of the system into the between group variance and wi...
  • NYC Bike Share Rebalancing - Duration: 29 minutes.

    • 1 month ago
    • 4 views
    As cities provide bike sharing services, they must also plan for how to redistribute bicycles as they inevitably build up at more popular destination stations. In this episode, Hui Xiong talks abou...
  • [MINI] Heteroskedasticity - Duration: 8 minutes, 59 seconds.

    • 1 month ago
    • 7 views
    Heteroskedasticity is a term used to describe a relationship between two variables which has unequal variance over the range.  For example, the variance in the length of a cat's tail almost ce...
  • [MINI] Random Forest - Duration: 12 minutes.

    • 1 month ago
    • 9 views
    Random forest is a popular ensemble learning algorithm which leverages bagging both for sampling and feature selection. In this episode we make an analogy to the process of running a bookstore.
  • [MINI] Survival Analysis - Duration: 14 minutes.

    • 1 month ago
    • 2 views
    Survival analysis techniques are useful for studying the longevity of groups of elements or individuals, taking into account time considerations and right censorship. This episode explores how surv...
  • [MINI] Gini Coefficients - Duration: 16 minutes.

    • 1 month ago
    • 5 views
    The Gini Coefficient (as it relates to decision trees) is one approach to determining the optimal decision to introduce which splits your dataset as part of a decision tree. To pick the right featu...
  • [MINI] Dropout - Duration: 15 minutes.

    • 1 month ago
    • 8 views
    Deep learning can be prone to overfit a given problem. This is especially frustrating given how much time and computational resources are often required to converge. One technique for fighting over...
  • [MINI] The Bootstrap - Duration: 10 minutes.

    • 1 month ago
    • 2 views
    The Bootstrap is a method of resampling a dataset to possibly refine it's accuracy and produce useful metrics on the result. The bootstrap is a useful statistical technique and is leveraged in Bagg...
  • [MINI] AdaBoost - Duration: 10 minutes.

    • 1 month ago
    • 28 views
    AdaBoost is a canonical example of the class of AnyBoost algorithms that create ensembles of weak learners. We discuss how a complex problem like predicting restaurant failure (which is surely...
  • [MINI] Generative Adversarial Networks - Duration: 9 minutes, 53 seconds.

    • 1 month ago
    • 70 views
    GANs are an unsupervised learning method involving two neural networks iteratively competing. The discriminator is a typical learning system. It attempts to develop the ability to recognize members...
  • Opinion Polls for Presidential Elections - Duration: 52 minutes.

    • 1 month ago
    • 14 views
    Recently, we've seen opinion polls come under some skepticism.  But is that skepticism truly justified?  The recent Brexit referendum and US 2016 Presidential Election are examples where ...
  • Kurzgesagt – In a Nutshell - Channel

    • 62 videos
    Videos explaining things with optimistic nihilism.

    We are a small team who want to make science look beautiful. Because it is beautiful.

    Currently we make one animation video per month. Follow us
    • CHANNEL
    4,277,819
to add this to Watch Later

Add to

Loading playlists...