The Adaptive AI™ Approach: Run Deep Neural Networks with Optimal Performance

If you are an AI engineer dissatisfied with the speed or power consumption of your neural network inferences and believe there are no solutions available for better performance….then keep reading! I’d like to introduce a new way to run your deep neural networks at their most optimal point. It is dynamic, context-aware, and flexible. It ...

How Latent AI’s LEIP SDK Improves Deep Learning Inference Efficiency

Our Latent AI Efficient Inference Platform (LEIP) is an SDK for deep learning training and inference. LEIP provides APIs to train, quantize, and deploy edge AI models from many deep learning frameworks. It then generates optimized runtime engines deployable in embedded devices and infrastructure edge devices. Latent AI’s LEIP SDK enables you to deploy deep ...

The Quantization Myth

Demystifying Quantization Do you need high bit-precision to operate neural networks? More specifically, do you need a high bit-precision processor to run neural network inferences in the same level of fidelity that you’ve trained them? These concepts seem to be popular myths but are not true. A large part of the confusion around these myths ...

Defining the Edge

Edge Computing Started with the Abacus Edge computing and edge AI are extremely popular tech buzzwords today.  Just do a quick Google search for this term and you’ll get about 233 million results in less than a few seconds. Yes, there’s an overwhelming amount of information about edge computing and especially the importance of moving ...

Scaling Edge AI in a Data Driven World, Part Two

The Essence of Edge AI Many applications today need edge computing. However, due to privacy issues, the need for real-time responses, and lack of network connectivity, applications are often compromised.  A similar position supporting edge computing comes from the argument around network scalability. The cost and latency for network backhaul can be problematic, especially when ...

Scaling Edge AI in a Data-Driven World, Part One

Scaling Edge AI in a Data-Driven World, Part One Drowning in Data We live in a data-driven world where IoT devices are always on, always tracking, and always monitoring. Being perpetually connected also means that we’re producing mind-boggling amounts of data. In fact, IDC Research predicts by 2020 we will be generating 44 trillion gigabytes ...

AI’s Shocking Carbon Footprint

AI’s Shocking Carbon Footprint How Techniques First Invented in the 1920s are Changing That Introduction What do the melting glaciers of Greenland have in common with artificial intelligence? On the surface, not much. But if you dig just a bit deeper, the connection is scarier than you might imagine. Turns out that data is not ...

The Era of Commercializing AI, Part Two

Supporting Efficient Workflow for Commercializing AI  At the early stage of AI commercialization, we are faced with the “dark ages” of tools, infrastructure, and approaches. There are many analogies that we can draw upon to understand where we truly are at this moment. For example, in the early days of the Internet, everyone was building ...

The Era of Commercializing AI, Part One

Beyond the Valley of Innovation Death Rapid success in deep learning algorithms has spawned new applications in video analytics, speech processing, and natural language processing. New smart products with compelling user experience, driven by the power of AI, can create safer human environments, allows us to work more efficiently, and helps to make communication easier. ...

Latent AI, Adaptive AI Optimized for Compute, Energy and Memory

Originally published in Petacrunch on August 9, 2019. Latent AI has raised $3.5M in total. We talk with Jags Kandasamy, its CEO. PetaCrunch: How would you describe Latent AI in a single tweet? Jags Kandasamy: Latent AI brings Adaptive AI™ to the edge through our core technologies and platform tools enabling efficient, adaptive AI optimized for compute, energy, and memory ...

AI Moves to the Edge

Edge is Where the Opportunity is and Why AI Needs to Evolve This is a 2-part series on the impact of AI on the edge as compared to the core, and why the approach to building AI algorithms needs to change if they are to operate more efficiently on the edge Introduction From enabling autonomous ...

It’s Time for Adaptive AI to Enable a Smarter Edge

Most of us are familiar with this scenario:  “Hey Siri (or insert your favorite ‘wake’ word for your digital voice assistant), turn on the hallway light.”  Instantly and magically, that hallway light turns on, and life is good. But then, reality kicks in, and all of a sudden your internet service provider is experiencing an ...

Newsletter Signup