Tag Machine Learning

Machine Learning and Technical Debt with D. Sculley Holiday Repeat

http://traffic.libsyn.com/sedaily/ml_techdebt_ad_free.mp3Podcast: Play in new window | DownloadOriginally published November 17, 2015 “Changing anything changes everything.” Technical debt, referring to the compounding cost of changes to software architecture, can be especially challenging in machine learning systems. D. Sculley is a software engineer at Google, focusing on machine learning, data mining, and information retrieval. He recently co-authored the paper Machine Learning: The High Interest Credit Card of Technical Debt. Questions How do

Continue reading…

Training the Machines with Russell Smith

http://traffic.libsyn.com/sedaily/RainforestQA.mp3Podcast: Play in new window | Download Automation is changing the labor market. To automate a task, someone needs to put in the work to describe the task correctly to a computer. For some tasks, the reward for automating a task is tremendous–for example, putting together mobile phones. In China, companies like FOXCONN are investing time and money into programming the instructions for how to assemble your phone. Robots execute

Continue reading…

Legal Technology with Justin Kan

http://traffic.libsyn.com/sedaily/LegalTechnology.mp3Podcast: Play in new window | Download Imagine that you are a lawyer. Your work involves managing files with dense, technical text. Your co-workers collaborate with you to accomplish a complex goal that can be broken down into smaller pieces. Your work has formal specifications, but there are degrees of freedom in how you express an idea. In all of these ways, the job of a lawyer is similar to

Continue reading…

Model Training with Yufeng Guo

http://traffic.libsyn.com/sedaily/ModelTraining.mp3Podcast: Play in new window | Download Machine learning models can be built by plotting points in space and optimizing a function based off of those points. For example, I can plot every person in the United States in a 3 dimensional space: age, geographic location, and yearly salary. Then I can draw a function that minimizes the distance between my function and each of those data points. Once I

Continue reading…

Tinder Engineering Management with Bryan Li

http://traffic.libsyn.com/sedaily/TinderManagement.mp3Podcast: Play in new window | Download Tinder is a rapidly growing social network for meeting people and dating. In the past few years, Tinder’s userbase has grown rapidly, and the engineering team has scaled to meet the demands of increased popularity. On Tinder, you are presented with a queue of suggested people that you might match with, and you swipe left or right to indicate that you like or

Continue reading…

Sports Deep Learning with Yu-Han Chang and Jeff Su

http://traffic.libsyn.com/sedaily/SportsAnalytics.mp3Podcast: Play in new window | Download A basketball game gives off endless amounts of data. Cameras from all angles capture the players making their way around the court, dribbling, passing, and shooting. With computer vision, a computer can build a well-defined understanding for what a sport looks like. With other machine learning techniques, the computer can make predictions by combining historical data with a game that is going on

Continue reading…

Deep Learning Systems with Milena Marinova

http://traffic.libsyn.com/sedaily/DeepLearningSystems.mp3Podcast: Play in new window | Download The applications that demand deep learning range from self-driving cars to healthcare, but the way that models are developed and trained is similar. A model is trained in the cloud and deployed to a device. The device engages with the real world, gathering more data. That data is sent back to the cloud, where it can improve the model. From the processor level

Continue reading…

Visual Search with Neel Vadoothker

http://traffic.libsyn.com/sedaily/Visual_Search.mp3Podcast: Play in new window | Download If I have a picture of a dog, and I want to search the Internet for pictures that look like that dog, how can I do that? I need to make an algorithm to build an index of all the pictures on the Internet. That index can define the different features of my images. I can find mathematical features in each image that

Continue reading…

Word2Vec with Adrian Colyer

http://traffic.libsyn.com/sedaily/Word2vecAdrianColyer.mp3Podcast: Play in new window | Download Machines understand the world through mathematical representations. In order to train a machine learning model, we need to describe everything in terms of numbers.  Images, words, and sounds are too abstract for a computer. But a series of numbers is a representation that we can all agree on, whether we are a computer or a human. In recent shows, we have explored how

Continue reading…

Artificial Intelligence APIs with Simon Chan

http://traffic.libsyn.com/sedaily/SalesforceEinstein.mp3Podcast: Play in new window | Download Software companies that have been around for a decade have a ton of data. Modern machine learning techniques are able to turn that data into extremely useful models. Salesforce users have been entering petabytes of data into the company’s CRM tool since 1999. With its Einstein suite of products, Salesforce is using that data to build new product features and APIs. Simon Chan

Continue reading…

Similarity Search with Jeff Johnson

http://traffic.libsyn.com/sedaily/SimilaritySearch.mp3Podcast: Play in new window | Download Querying a search index for objects similar to a given object is a common problem. A user who has just read a great news article might want to read articles similar to it. A user who has just taken a picture of a dog might want to search for dog photos similar to it. In both of these cases, the query object is

Continue reading…

Self-Driving Deep Learning with Lex Fridman

http://traffic.libsyn.com/sedaily/SelfDrivingDeepLearning.mp3Podcast: Play in new window | Download Self-driving cars are here. Fully autonomous systems like Waymo are being piloted in less complex circumstances. Human-in-the-loop systems like Tesla Autopilot navigate drivers when it is safe to do so, and lets the human take control in ambiguous circumstances. Computers are great at memorization, but not yet great at reasoning. We cannot enumerate to a computer every single circumstance that a car might

Continue reading…

Reinforcement Learning with Michal Kempa

http://traffic.libsyn.com/sedaily/ReinforcementLearning.mp3Podcast: Play in new window | Download Reinforcement learning is a type of machine learning where a program learns how to take actions in an environment based on how that program has been rewarded for actions it took in the past. When program takes an action, and it receives a reward for that action, it is likely to take that action again in the future because it was positively reinforced.

Continue reading…

Apparel Machine Learning with Colan Connon and Thomas Bell

http://traffic.libsyn.com/sedaily/ApparelMachineLearning.mp3Podcast: Play in new window | Download In its most basic definition, machine learning is a tool that makes takes a data set, finds a correlation in that data set, and uses that correlation to improve a system. Any complex system with well-defined behavior and clean data can be improved with machine learning. Several precipitating forces have caused machine learning to become widely used: more data, cheaper storage, and better

Continue reading…

Instacart Data Science with Jeremy Stanley

http://traffic.libsyn.com/sedaily/InstacartDataScience.mp3Podcast: Play in new window | Download Instacart is a grocery delivery service. Customers log onto the website or mobile app and pick their groceries. Shoppers at the store get those groceries off the shelves. Drivers pick up the groceries and drive them to the customer. This is an infinitely complex set of logistics problems, paired with a rich data set given by the popularity of Instacart. Jeremy Stanley is

Continue reading…

Distributed Deep Learning with Will Constable

http://traffic.libsyn.com/sedaily/Distributeddeeplearning.mp3Podcast: Play in new window | Download Deep learning allows engineers to build models that can make decisions based on training data. These models improve over time using stochastic gradient descent. When a model gets big enough, the training must be broken up across multiple machines. Two strategies for doing this are “model parallelism” which divides the model across machines and “data parallelism” which divides the data across multiple copies

Continue reading…

Video Object Segmentation with the DAVIS Challenge Team

http://traffic.libsyn.com/sedaily/objectsegmentation.mp3Podcast: Play in new window | Download Video object segmentation allows computer vision to identify objects as they move through space in a video. The DAVIS challenge is a contest among machine learning researchers working off of a shared dataset of annotated videos. The organizers of the DAVIS challenge join the show today to explain how video object segmentation models are trained and how different competitors take part in the

Continue reading…

Data Skepticism with Kyle Polich

http://traffic.libsyn.com/sedaily/dataskeptic_edited.mp3Podcast: Play in new window | Download With a fast-growing field like data science, it is important to keep some amount of skepticism. Tools can be overhyped, buzzwords can be overemphasized, and people can forget the fundamentals. If you have bad data, you will get bad results in your experimentation. If you don’t know what statistical approach you want to take to your data, it doesn’t matter how well you

Continue reading…

Poker Artificial Intelligence with Noam Brown

http://traffic.libsyn.com/sedaily/Libratus.mp3Podcast: Play in new window | Download Humans have now been defeated by computers at heads up no-limit holdem poker. Some people thought this wouldn’t be possible. Sure, we can teach a computer to beat a human at Go or Chess. Those games have a smaller decision space. There is no hidden information. There is no bluffing. Poker must be different! It is too human to be automated. The game

Continue reading…

Convolutional Neural Networks with Matt Zeiler

http://traffic.libsyn.com/sedaily/ClarifaiCNNs.mp3Podcast: Play in new window | Download Convolutional neural networks are a machine learning tool that uses layers of convolution and pooling to process and classify inputs. CNNs are useful for identifying objects in images and video. In this episode, we focus on the application of convolutional neural networks to image and video recognition and classification. Matt Zeiler is the CEO of Clarifai, an API for image and video recognition.

Continue reading…