Gradients for Everyone: A Quick Guide to Autodiff in Julia
Explore automatic differentiation in Julia, comparing approaches with Python frameworks and learning to make code differentiable for various backends. Gain insights into forward and reverse modes, custom rules, and performance optimization.
The State of Julia in 2021 - JuliaCon Keynote
Comprehensive overview of Julia's progress in 2021, covering threading, compiler improvements, linear algebra advancements, package updates, and future development plans.
Transformations and Automatic Differentiation in Computational Thinking - Lecture 3
Explore transformations and automatic differentiation in Julia, covering linear and non-linear transformations, function types, and applications in machine learning, with practical examples and visualizations.
Loop Analysis and Vectorization in Julia - JuliaCon 2020
Explore LoopVectorization.jl for efficient loop representation, cost modeling, and vectorization strategies in Julia, enhancing performance through intra-core parallelism and SIMD operations.
Flux - The Elegant Machine Learning Library for Julia
Explore Flux, an intuitive machine learning library for Julia, featuring state-of-the-art performance, automatic differentiation, and innovative compiler technology for efficient and flexible ML development.
Tricks and Tips in Numerical Computing - Keynote
Explore advanced numerical computing techniques, from complex differentiation to low-precision arithmetic, with insights on error analysis, matrix operations, and IEEE standards for improved computational accuracy and efficiency.
Swift for TensorFlow - The Next-Generation Machine Learning Framework
Explore language-integrated automatic differentiation and optimized tooling in Swift for TensorFlow, enhancing machine learning productivity and innovation.
Physics-Informed Automatic Differentiation in Scientific Simulations
Explore how automatic differentiation intersects with physical symmetries and numerical analysis in scientific simulations, focusing on materials science applications in DFTK.jl.
Real-Time Airborne Magnetic Navigation with MagNav.jl
Discover how MagNav.jl enables real-time magnetic navigation by compensating aircraft magnetic fields and implementing advanced navigation filters using Julia's powerful features.
Computational Models of Cognition - Reverse-Engineering Common Sense in the Human Mind and Brain Pt 1
Explore cognitive modeling to reverse-engineer human common sense, examining AI progress, scientific context, and probabilistic programming techniques for capturing learning and constructing models.
Physics-Constrained Reservoir-Computing for Turbulence and Chaotic Learning
Explore physics-constrained reservoir-computing for turbulence and chaotic learning, combining physical principles with empirical modeling to predict and optimize complex fluid flows in aerospace propulsion and turbulence.
Computational Optimal Transport - A Mini Tutorial
Overview of novel approaches to compute optimal transport, blending recent techniques including convex optimization, automatic differentiation, and neural networks for large-scale approximations in high-dimensional regimes.
Programming Languages for High-Assurance Vehicles
Explore secure programming for high-assurance vehicles using embedded domain-specific languages in Haskell, focusing on autopilot development, verification tools, and real-world applications.
TensorCircuit - A Quantum Software Framework for the NISQ Era
Explore TensorCircuit, an advanced quantum circuit simulator leveraging tensor networks and machine learning frameworks for enhanced quantum computing simulation and variational algorithms.
Automatic Differentiation - Session Preview at POPL 2023
Explore automatic differentiation techniques and their applications in programming languages, presented by expert Sasa Misailovic at POPL 2023.
Synthesizing Precise Static Analyzers for Automatic Differentiation
Explore Pasado, a technique for synthesizing precise static analyzers for Automatic Differentiation, improving precision in nonlinear operations and demonstrating applications in various domains.
Probabilistic Programming with Programmable Variational Inference
Explore a modular approach to variational inference in probabilistic programming, enhancing expressiveness and enabling user-defined objectives with systematic gradient estimation transformations.
Federated Automatic Differentiation - Seminar 96
Explore advanced concepts in federated automatic differentiation with Google researcher Zachary Charles, covering innovative approaches to distributed machine learning and privacy-preserving computation.
Efficient and Modular Implicit Differentiation - Machine Learning Research Paper Explained
Explores a unified framework for implicit differentiation in machine learning, enabling automatic differentiation of optimization problems without manual derivations or loop unrolling, with applications in meta-learning and hyperparameter optimization.
JAX Crash Course - Accelerating Machine Learning Code
Accelerate machine learning with JAX: Learn NumPy-like operations on CPU, GPU, and TPU, automatic differentiation, and high-performance techniques for ML research in this comprehensive introduction.
PyTorch - A Modern Library for Machine Learning with Adam Paszke
Explore PyTorch's capabilities in machine learning, from research to production. Learn about its innovative solutions for efficient inference and its versatility across various ML scenarios.