deep modules

Max Tegmark's MIT CBMM talk on why deep learning works so well. He argues that the laws of physics and the symmetries in physical data make it compressible into small neural networks, tying physics to network structure.

Geoff Hinton's 2010 Google Tech Talk on deep belief networks, learning layers of representation one at a time from unlabeled data, and extending them with multiplicative interactions.

John Ousterhout, Stanford professor and creator of Tcl, presents the ideas of his book A Philosophy of Software Design in a Talks at Google session. He covers managing complexity, deep modules and interfaces, and what he teaches in his Stanford software design course.

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.

Valve's John McDonald presents at GDC 2018 on how Valve uses deep learning (VACnet) to detect cheaters in Counter-Strike: Global Offensive. He covers training on human-reviewed replays and how model output is confirmed by manual review.

A GDC 2018 talk by Valve's John McDonald on VACNet, a deep learning system that analyzes CS:GO gameplay to detect cheaters. It covers how the model is trained on human-reviewed Overwatch cases and how its output feeds human moderation.

Bill Dally of NVIDIA gives a Hot Chips 2023 keynote on the challenges of building hardware for deep learning. He traces how GPUs have been adapted for machine learning, especially training.

A DeepSec 2010 conference talk by Ralf Philipp Weinmann on attacking the baseband processor of mobile phones rather than the application processor. It covers how open-source GSM base stations make malicious-tower attacks practical against neglected GSM stacks.

Rick Houlihan's AWS re:Invent 2018 deep dive on advanced DynamoDB design patterns. It covers index overloading, GSI sharding, composite keys, graph processing and transactions.

Brian Karis's SIGGRAPH 2021 talk explains how Unreal Engine 5's Nanite virtualized geometry works. It covers mesh import, the data structures, streaming, decompression, culling, software and hardware rasterization, and shading.

Sean Carroll's Talks at Google presentation of his book Something Deeply Hidden. He gives an accessible introduction to quantum mechanics and argues for the many-worlds interpretation and the emergence of spacetime.

Inventor Mary Lou Jepsen demonstrates using red light and sound to see inside the body and brain, aiming at tumor detection and neural activity measurement, and potentially a cheaper wearable MRI replacement.

Demis Hassabis of DeepMind speaks at Google Zeitgeist, saying human-level AI is decades away but the debate should start now. He covers DeepMind's focus on game-playing agents.

Quentin Perret of Google gives a technical deep dive into protected KVM (pKVM) on Arm64, a confidential computing approach for CPUs without hardware extensions. It explains how the nVHE hypervisor manages stage-2 MMU access control to protect guest memory.

Rich Hickey's philosophical talk from the first Clojure Conj in 2010. He argues that good design comes from deliberate, away-from-keyboard thinking, and describes how to feed the background mind so it solves problems.

Adam Conover's talk at a millennial marketing conference argues that generations are an unscientific, condescending idea and that millennials do not exist as a real category. The description notes that researcher Jean Twenge later said he misrepresented some of her work.

A conference presentation by Bert Hubert on how companies lose their technological edge and become outsourcing hubs. It argues the same dynamic applies to whole countries and continents, and ends with suggestions for reversing it.

Ali Rahimi's NIPS 2017 Test-of-Time award talk, in which he argues that modern machine learning has become alchemy, working without being rigorously understood. He calls for more rigor and understanding in the field.

A Microsoft Build 2019 session in which the WSL team explains the new WSL 2 architecture, which runs a real Linux kernel alongside Windows on a hypervisor. It covers faster file performance, Linux file access from Windows and better application support.

Mobileye co-founder and CTO Amnon Shashua explains what goes into sensing for autonomous driving and whether end-to-end deep learning can work for it. He argues for decomposing the problem.

An AWS re:Invent 2019 session for advanced DynamoDB users on design patterns used by large customers, including Amazon retail. It covers GSI sharding, index overloading, graph processing, composite keys and transactional workflows.

Ron Garret tells the story of the Remote Agent Experiment on NASA's Deep Space 1, where autonomous software controlled a spacecraft in 1999. He describes debugging Lisp code remotely from millions of miles away.

An AWS re:Invent 2018 session diving into the Nitro system, a set of hardware offload and security building blocks behind next-generation EC2 instances. It covers the design and architecture and how Nitro enables new instance types.

Ali Rahimi accepts the NIPS 2017 Test of Time Award and argues that machine learning has become alchemy, with practice running ahead of understanding.

Geoffrey Hinton's Google Tech Talk linking machine learning to biology, explaining dropout as a form of model averaging and why sexual reproduction and stochastic spiking neurons may prevent overfitting.

Simon Knowles, co-founder and CTO of Graphcore, talks about "intelligence processors", chips designed specifically for machine learning. The talk was given at the RAAIS 2017 summit and covers Graphcore's architecture.

Apple security head Ivan Krstic gives a Black Hat 2016 talk on iOS security, covering HomeKit, Auto Unlock and iCloud Keychain. He explains key hierarchies and how data can stay safe even in adversarial clouds.

Jack Diederich's PyCon 2012 talk argues that classes are overused in Python and walks through real code, refactoring away unnecessary classes, exceptions and modules. It popularized the heuristic that a class with two methods, one being __init__, should be a function.

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.

Joe Armstrong, co-inventor of Erlang, gives a funny and opinionated Strange Loop talk on the tangled state of software: build tools, package managers, entropy and the physical limits of computation. He argues for ideas like naming things by content hash and throwing away your first version.

Bruce Dang of Microsoft gives a 27C3 talk on how the Stuxnet vulnerabilities were found and analyzed. He walks through the techniques used to triage them and the details of each zero-day exploit, down to the opcode level.

Martin Kleppmann's GOTO Berlin 2016 talk on how collaborative editors, offline apps, and multi-datacenter databases handle concurrent updates. It covers conflict resolution approaches including operational transformation and CRDTs, with a worked look at text CRDTs.

Andrei Alexandrescu's CppCon 2019 talk revisits sorting, showing how branchless tricks, hybrid strategies and a cost metric can speed up std::sort-style algorithms on modern hardware.

Mark Seemann argues that functional programming naturally yields many of the best practices object-oriented developers learn painfully. He shows how functional architecture leads to a pit of success, with a pure core and impure shell.

Deviant Ollam and Howard Payne give an in-depth DEF CON 22 explanation of how elevators work, from the pit to the penthouse. It covers their control modes and how pen testers use elevators to bypass building security.

Herb Sutter's deep C++ and Beyond 2012 talk on atomics and the C++ memory model, covering why programmers chasing top performance need to understand hardware ordering. This is part one of two.

A 2007 Google Tech Talk in which Cliff Click of Azul Systems presents a lock-free concurrent hash table that scales to 768 CPUs. He explains why it is correct by reasoning in a different way than usual happens-before and memory-order arguments.

Christopher Alexander's keynote at OOPSLA 1996 on patterns in architecture, addressed to the software community. He moves beyond patterns toward deeper ideas of wholeness and living structure.

Dylan Beattie's conference talk explores the history and mess behind plain text: encodings, Unicode, line endings and the many ways text goes wrong. It argues that the tidy idea of plain text hides a lot of complexity underneath everyday software.

A 2018 GDC talk by NetherRealm's Michael Stallone on the engine changes, optimizations and tooling needed to roll back and re-simulate up to 8 frames in 16 ms in Mortal Kombat and Injustice 2. It is a deep dive into deterministic rollback netcode.