feature visualization

Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.

Christopher Domas presents his Cantor Dust tool at Derbycon 2012, a 3D visual approach to reverse engineering binaries by visualizing their structure dynamically.

Christopher Domas's REcon 2013 talk on dynamic binary visualization for reverse engineering. He shows how rendering binary data as interactive visual maps and trigraphs reveals structure that hex dumps hide, leading to his Cantor.dust tool.

Bret Victor's talk on Drawing Dynamic Visualizations. It argues that visualization tools offer either the directness of hand drawing or the dynamics of programmed graphics, and shows a tool that combines both.

Guy Steele's JuliaCon 2016 keynote on the Fortress language, its features and the lessons learned from the project.

Philip Roberts explains the JavaScript event loop, call stack, callbacks and asynchronous behavior with live visualizations using a tool he built. It demystifies terms like non-blocking and single-threaded.

Damian Conway's hour-long keynote at the Perl conference, On the Shoulders of Giants, showing off Perl 6 (Raku) features with history, algorithms and a quantum math operator built with grammars. It is delivered with comic flair.

Bryan Cantrill of Joyent presents Manta, an internet-facing object store that lets you run compute directly on the data. The talk is peppered with ZFS history and Cantrill's trademark commentary on the industry.

Anna Rosling Rönnlund presents Dollar Street, a project photographing homes in dozens of countries, from stoves to beds to toilets, and sorting them by income. She shows how data visualization can change how we see the world.

A Google Tech Talk by Laurens van der Maaten, co-creator of t-SNE, on visualizing high-dimensional data by mapping it to two dimensions. It explains how the technique works and how it compares with other visualization approaches.

SciPy 2015 talk by Nathaniel Smith and Stefan van der Walt on choosing a new default colormap for Matplotlib. It covers why Jet misleads, how perceptual color spaces work, and how viridis was designed.

Drew Berry shows scientifically accurate animations of molecular processes inside cells, such as DNA replication, at TEDxSydney.

Rob Pike's dotGo 2015 talk argues that Go only seems simple, and that its simplicity hides real complexity that is part of the design. He explains the thinking behind Go's restraint in features.

Hans Rosling uses the Gapminder animated-data tool to debunk myths about world development, with sportscaster-like energy. It shows trends in health, income and child survival across countries.

Steven Wittens' JSConf US 2013 talk on drawing with WebGL, using animated visuals to walk through vectors, matrices and the rendering pipeline. Despite the title, it works as a visual primer on the linear algebra behind 3D graphics.

Bret Victor's talk proposing a new kind of maker space built for seeing and understanding a project's behavior: inside it, across time and across possibilities. It argues for scientific understanding over recipes and rules of thumb.

In this TED talk, Hans Rosling uses animated statistics to debunk myths about the developing world, showing how health and income have improved across countries.

Peter Seibel's 2006 Google TechTalk on Practical Common Lisp, framed by the Sapir-Whorf hypothesis and Paul Graham's Blub paradox. It shows Lisp features such as condition restarts and its generic-function object system.

Stephen Kell's Strange Loop talk argues that C and Unix already contain Smalltalk-like dynamism and introspection that can be exposed. He presents his liballocs research on bridging dynamic and compiled languages.

A Foresight Institute workshop video with two talks: Shawn Douglas on nanoscale instruments for visualizing small proteins, and Bret Victor on Dynamicland. Victor's part shows biomolecular design built in his Realtalk system with physical objects.

Hans Rosling's TED@Cannes talk uses boxes and animated data graphics to show how world population will grow to about 9 billion. He argues that raising living standards for the poorest is what reduces population growth.

Yehuda Katz's Railsberry 2012 talk on why Rails is hard to learn and use. He explains that the framework's many features reflect real complexity in web applications that newcomers do not yet see.

Matt Godbolt tells the story of Compiler Explorer, from a hacky basement server to a cloud-scaled service handling tens of thousands of daily requests. He also shows its features and how it is built.

Markus Winand shows how SQL has evolved since SQL-92, comparing old-style solutions to modern features such as window functions and system versioning, and notes that many developers never learn them.

Scott Chacon's FOSDEM 2024 talk on lesser-known Git tips and tricks: useful config settings, older and newer commands, monorepo and big-repo features, and recent GitHub additions. It closes with why he is now building GitButler, followed by a Q&A.

A HOPE09 talk on how modern computer chips are manufactured, from 22nm transistors to ultra-clean fabs and the tricks used to pattern tiny features with light. It frames chipmaking as hacking electrical engineering and physics.

Douglas Crockford's 2009 Google tech talk on the good and bad parts of JavaScript, based on his book. He argues for using a reliable subset of the language and avoiding its flawed features.

A thoughtbot meetup talk by Max Cantor on getting most of what popular plugins provide using only built-in Vim features. It covers autocomplete, file jumping, filesystem navigation, build integration and snippets, with slides and a vimrc available.

Raymond Hettinger's PyCon 2013 talk on transforming code into idiomatic Python through a series of before-and-after refactorings. It shows how to use iterators, dictionaries, named tuples and other language features well.

Rob Pike's Google I/O 2012 talk shows how goroutines and channels solve tricky concurrency problems with simple Go code. It features a playful goroutine demo with gophers passing messages and a search engine example.

Deviant Ollam's two-hour conference talk explains how elevators work, from the pit and buffers to the car top, controller logic and access-control features. It shows how this knowledge can be used for optimization and for bypassing building security.

Stefan Karpinski's European Lisp Symposium 2016 talk asks whether Julia is a Lisp. He covers the features it borrows from Lisp, such as macros and closures, and where it departs, including syntax and its type system, with generated machine code shown.

Chris Urmson's SXSW 2016 talk on Google's self-driving car project, covering 1.3 million self-driven miles and the gap between hype and reality. It shows sensor visualizations and playbacks of hard situations the cars met, and discusses failures such as the low-speed bus collision.

Zig creator Andrew Kelley justifies why Zig exists and tours its distinctive features, including C interoperability and comptime, along with what people had built and what 1.0 would bring. It was given at Philly ETE 2019.

Morphcat Games explains how they fit Micro Mages, a full-featured NES game, into 40 kilobytes. It covers compression of sprites and level layouts and other space-saving tricks.

Vim creator Bram Moolenaar's 2007 Google Tech Talk on habits for efficient text editing. He explains how to spot repetition and inefficiency, then use editor features to fix it.

A HOPE X talk giving an in-depth explanation of how elevators work, from their history in hacker culture to using their control systems to bypass building security. It covers features and abilities of elevators that most people never see.

Brandon Rhodes' PyOhio 2014 talk on applying the Clean Architecture in Python. He shows how this high-level design pattern fits Python's features and addresses maintainability problems in large applications.

Greg Law's 15-minute CppCon 2015 lightning talk shows what GDB can do beyond basic use, including its text user interface and reverse debugging.

A 2008 Google Tech Talk in which Slava Pestov introduces Factor, a concatenative language influenced by Forth, Lisp and Smalltalk. It covers the interactive environment, metaprogramming, and the language's modern high-level features and libraries.