State-Space Models (SSMs) have emerged as efficient alternatives to transformers for sequential data tasks, offering linear or near-linear scalability with sequence length, making them ideal for long-sequence applications in NLP, vision, and edge AI, including real-time transcription, translation, and contextual search. These applications require lightweight, high-performance models for deployment on resource-constrained devices like laptops and PCs. Designing specialized accelerators for every emerging neural network is costly and impractical; instead, optimizing models for existing NPUs in AI PCs provides a scalable solution. To this end, we propose XAMBA, the first framework to enable and optimize SSMs on commercial off-the-shelf (COTS) state-of-the-art (SOTA) NPUs. XAMBA follows a three-step methodology: (1) enabling SSMs on NPUs, (2) optimizing performance to meet KPI requirements, and (3) trading accuracy for additional performance gains. After enabling SSMs on NPUs, XAMBA mitigates key bottlenecks using CumBA and ReduBA, replacing sequential CumSum and ReduceSum operations with matrix-based computations, significantly improving execution speed and memory efficiency. Additionally, ActiBA enhances performance by approximating expensive activation functions (e.g., Swish, Softplus) using piecewise linear mappings, reducing latency with minimal accuracy loss. Evaluations on an Intel Core Ultra Series 2 AI PC show that XAMBA achieves up to 2.6X speed-up over the baseline. Our implementation is available at https://github.com/arghadippurdue/XAMBA.

Artificial Intelligence, or AI, is one of the fastest-growing industries today, with a projected market size of over $300 billion by 2025. As more and more companies embrace AI to drive growth and innovation, investors are looking to capitalize on this trend by investing in AI stocks. In this blog post, we will take a closer look at the top 10 AI stocks to buy in 2023. Google's parent company, Alphabet, is a leader in AI technology. The company has invested heavily in AI, with its Google Brain project and DeepMind acquisition.

In this article, we discuss the future of artificial intelligence, including 10 predictions about 10 companies. The future of artificial intelligence (AI) is a topic of much speculation and debate. Some experts believe that AI has the potential to revolutionize many aspects of society and industry, while others are more cautious about its potential impact. The artificial intelligence sector is thriving across the globe. AI-enabled tools, like smarter chat-bots for customer service and robots for self-service at banks, are gaining traction in the mainstream.

WIRE)--What's New: Today, Intel announced the 2023 release of the Intel oneAPI tools – available in the Intel Developer Cloud and rolling out through regular distribution channels. The new oneAPI 2023 tools support the upcoming 4th Gen Intel Xeon Scalable processors, Intel Xeon CPU Max Series and Intel Data Center GPUs, including Flex Series and the new Max Series. The tools deliver performance and productivity enhancements, and also add support for new Codeplay1 plug-ins that make it easier than ever for developers to write SYCL code for non-Intel GPU architectures. These standards-based tools deliver choice in hardware and ease in developing high-performance applications that run on multiarchitecture systems. "We're seeing encouraging early application performance results on our development systems using Intel Max Series GPU accelerators – applications built with Intel's oneAPI compilers and libraries. For leadership-class computational science, we value the benefits of code portability from multivendor, multiarchitecture programming standards such as SYCL and Python AI frameworks such as PyTorch, accelerated by Intel libraries. We look forward to the first exascale scientific discoveries from these technologies on the Aurora system next year."

You can find the full source code to today's demo in a Kaggle notebook where it is formatted as a series of very short, numbered blocks. For the sake of brevity, this post will walk through only the most significant snippets of the notebook's code. But, of course, you can study the full notebook at your leisure by the block number and learn how we trained a neural network from scratch to achieve a level of accuracy not possible a decade ago. In blocks 1 to 3, the notebook sets the Python environment for TensorFlow. In blocks 4 to 14, the notebook loads the database MNIST, which is what we will use to create a model that can recognize handwritten digits and train our neural networks. Then the new and exciting part Intel offers today is how these models can be optimized on Intel hardware to run more efficiently and quickly.

It's no secret that artificial intelligence (AI) is one of the hottest topics in the tech world today. Every day, it seems like there's a new story about how AI is being used to improve some aspect of our lives, from personal assistants to driverless cars. Given all the hype, it's no wonder that educators are eager to introduce AI concepts to their students. Now, thanks to resources inside Intel's 5-module teaching kit for AI inference teaching the Intel Distribution of OpenVINO toolkit, it is easier than ever to introduce the concepts of deep learning AI to students. Get your students hands-on coding experience with this teacher kit, which comes with a lesson plan, 5-modules of workbooks, videos, quizzes, and Jupyter* Notebook coding lab tutorials.

Are you tired of switching between Windows and Linux environments to perform machine learning (ML) tasks? Do you want to accelerate inference of your ML applications in an effective way? This blog post is intended to serve as a guide to configure your Windows based system to get the most out of your Intel Integrated Graphics Processing Unit (iGPU). Now let's see how Intel's iGPU works with a Linux distribution (such as Ubuntu, openSUSE, Kali, Debian, Arch Linux, and more) on WSL to see the performance benefits of OpenVINO . I gave this combination of tools a try, with the demo shown below, and was really amazed by how seamlessly it works -- not to mention, with added acceleration!

Almost universally, today's systems must operate within limited system-level power budgets. For these power-bound systems, saving energy anywhere in the system enables more energy for compute and hence higher system performance. A tantalizing opportunity exists to achieve system-energy savings by keeping data commutes between memory and processing as short as possible. Energy savings should be the primary goal, our North Star for computing near memory. At the recent International Solid-State Circuits Conference (ISSCC), I gave a presentation titled: "We have rethought our commute; Can we rethink our data's commute?"

Open Federated Learning (OpenFL) is a deep learning framework agnostic library for federated learning developed at Intel that lets developers train statistical models on sharded datasets, distributed across several nodes (if you are new to OpenFL, refer to the OpenFL medium article). With the release of OpenFL 1.3, we incorporated a lot of exciting features such as flexible task assignment in the interactive API, new support and examples for Huggingface transformers, Pytorch Lightning, MXNet and Numpy, and new aggregation algorithms like FedCurv, FedYogi and FedAdam. But today we focus on a new dimension for our framework: bringing together hardware and software for privacy preserving AI using Intel Software Guard Extensions (Intel SGX) and Gramine. OpenFL was created to address the challenge of maintaining data privacy while bringing together insights from many disparate, confidential or regulated datasets. However, training a model this way introduces new challenges around IP and how it gets used.

Arnav Bawa, a student in the artificial intelligence program at Chandler Gilbert Community College, has developed an AI application to interpret EEG brain wave scans. The application can help predict brain seizures, so a patient can take medication or prevent injury from falling. William Glover, a student in the artificial intelligence program at Chandler Gilbert Community College, has developed an AI application for drones. The application can be used in indoor search and rescue situations. It uses AI to interpret a live video feed to look for and recognize people who may be trapped in a burning building.