Differentiable Programming: Theory, Function Fitting, and Practical Implementations

Differentiable programming augments traditional code with automatic differentiation, enabling gradient‑descent optimization of scientific and UI functions; the article surveys its theory, demonstrates fitting a damping curve via logistic and polynomial models in Julia, Swift, and TensorFlow, and discusses trade‑offs between analytical interpretability and neural‑network flexibility.

Differentiable ProgrammingJavaScriptTensorFlow

0 likes · 30 min read

Differentiable Programming: Theory, Function Fitting, and Practical Implementations

Liangxu Linux

Jan 27, 2020 · Fundamentals

How 99 Lines of Taichi Code Enable High‑Performance CG Simulations

Taichi, a Python‑embedded DSL created by an MIT PhD, dramatically speeds up material point method simulations—achieving up to 188× faster than TensorFlow—while keeping code concise, enabling differentiable physics for graphics and AI research.

Differentiable ProgrammingHigh‑performance computingMaterial Point Method

0 likes · 9 min read

How 99 Lines of Taichi Code Enable High‑Performance CG Simulations

Programmer DD

Jan 18, 2020 · Artificial Intelligence

How 99 Lines of Code Let You Create Frozen Magic with Taichi’s Differentiable Physics

Taichi, a Python‑embedded domain‑specific language created by MIT PhD Hu Yuanming, enables high‑performance, differentiable computer‑graphics simulations—ranging from ice‑snow effects to 3D fluids—using just a few dozen lines of code, dramatically outperforming TensorFlow and PyTorch while simplifying research pipelines.

AIDifferentiable ProgrammingMLSM-PM

0 likes · 9 min read

How 99 Lines of Code Let You Create Frozen Magic with Taichi’s Differentiable Physics

21CTO

Jan 13, 2020 · Fundamentals

How 99 Lines of Code Let You Create Frozen‑Style Magic with Taichi

Taichi, a new CG programming language created by MIT PhD student Hu Yuanming, enables high‑performance physical simulation and differentiable programming with just a few dozen lines of code, dramatically outperforming TensorFlow and PyTorch, and has been showcased in SIGGRAPH, ICRA, ICLR papers and real‑time demos.

Differentiable ProgrammingMLSM‑MPMPhysical Simulation

0 likes · 10 min read

How 99 Lines of Code Let You Create Frozen‑Style Magic with Taichi