Leveraging the power of C++ for efficient machine learning on embedded devices Adrian Stanciu adrian.stanciu.pub@gmail.com CppCon, 2023 1 / 50About me ◮ I am a software engineer from Romania ◮ I have Image classification ◮ Hand gesture recognition ◮ Summary ◮ Q&A 4 / 50Motivation 5 / 50Machine Learning (ML) ◮ Subfield of Artificial Inteligence (AI) ◮ Enables computers to learn from data and then consumption ◮ May have real-time performance constraints 7 / 50Machine learning on embedded devices ◮ Alternative to cloud-based machine learning ◮ Advantages: ◮ Real-time processing ◮ Low latency ◮ Reduced bandwidth

micrograd++: A 500 line C++ Machine Learning Library Gautam Sharma Independent Researcher gautamsharma2813@gmail.com Abstract—micrograd++ is a pure C++ machine learning li- brary inspired by Andrej Karpathy’s for building and training machine learning models. By leveraging the performance efficiency of C++, micro- grad++ offers a robust solution for integrating machine learning capabilities directly into C++-based Traditionally, all machine learning libraries are extremely bulky and very hard to integrate as third party dependencies. This aspect scares practitioners to adopt a C++ based machine learning library for prototyping

Intelligence,’ a term he coined 1/62: Arthur Samuel, an IBM computer scientist, creates a self-learning program that proves capable of defeating a top USA checkers champion AI ‘Winter1’ (1967-1996) Shakey, the first general- purpose mobile robot that can reason about its own actions 5/97: Deep Blue, IBM’s chess- playing computer, defeats Garry Kasparov, the world chess champion Trending = Unprecedented37 Machine-Learning Model* Trending = In 2015... Industry Surpassed Academia as Data + Compute + Financial Needs Rose *Machine Learning = A subset of AI where machines learn

step. How it started Morgan Stanley’s first eval focused on making their financial advisors more efficient and effective. The premise was simple: If advisors could access information faster and reduce the people. AI amplifies our potential and helps us be more efficient and creative. Elena Alfaro Head of Global AI Adoption Product Note: With deep research, ChatGPT can do work independently. Give it a prompt employee productivity and gives them access to deep, detailed research on any topic in minutes. In an internal evaluation by experts across domains, deep research saved an average of 4 hours per complex

the model uses to predict a specific output. You don’t need to be a data scientist or a machine learning engineer – everyone can write a prompt. However, crafting the most effective prompt can be complicated model’s ability to provide meaningful output. You don’t need to be a data scientist or a machine learning engineer – everyone can write a prompt. Prompt Engineering February 2025 7 When you chat with temperature control can be understood in a similar way to the softmax function used in machine learning. A low temperature setting mirrors a low softmax temperature (T), emphasizing a single, preferred

Canada ● Chair of Programming Languages for Standards Council of Canada Chair of WG21 SG19 Machine Learning Chair of WG21 SG14 Games Dev/Low Latency/Financial Trading/Embedded ● Editor: C++ SG5 Transactional hardware with built-in reduction operation acceleration. • Work group and subgroup algorithms • Efficient parallel operations between work items • Class template argument deduction (CTAD) and template boilerplate code and streamlines the use of C++ software design patterns • Expanded interoperability • Efficient acceleration by diverse backend acceleration APIs • SYCL atomic operations are now more closely

language and we won't be able to cover all of it in a few days. Some non-goals of this course are: • Learning how to develop macros: please see Chapter 19.5 in the Rust Book and Rust by Example instead. Assumptions Rust 1 hour and 5 minutes Deep Dives In addition to the 4-day class on Rust Fundamentals, we cover some more specialized topics: Rust in Android The Rust in Android deep dive is a half-day course on runs and make sure they work when you run them by hand. 15 Rust in Chromium The Rust in Chromium deep dive is a half-day course on using Rust as part of the Chromium browser. It includes using Rust in

a kind of failure that is the opposite of defects and outages.  Trying things out is a way of learning in the Agile world; it is a kind of feedback cycle that lets us make good decisions in the normal more quickly and with more good information available.  “Failing” in this sense is simply an efficient process we use to select among alternatives. Shadow IT Agile ways of working support a community The critical change is that of moving from a plan-driven approach to an Agile approach, based on learning and adapting. This is deeply opposed—let me say that again—deeply opposed to the control paradigm

Transactions on Information Theory, 2(3), 61-79. 【3】Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." nature 529.7587 (2016): 484-489. 【4】 Wei, Jason, et al. "Chain-of-thought Processing Systems 36 (2024). 【8】https://huggingface.co/spaces/mteb/leaderboard 【9】https://github.com/deep-floyd/IF 【10】https://developer.nvidia.com/blog/pushing-the-boundaries-of-speech-recognition-with-nemo-parakeet-asr- 在 IntelliJ IDEA 中，我们可以看到 AI 功能的加入，如：原生的向量化模型、基于语义化搜 索（SearchEverywhere）、结合补全统计的机器学习补全插件 Machine Learning Code Completion、适用于单个代码行的 Full Line Code Completion 等等。 而除了 GitHub Copilot 工具本身，它还开放了其插件能力，使得我们可以定义自己的