Some thoughts from the creator of an open source machine learning platform focused on developers.
Machine learning has, historically, been the purview of data science teams. This makes it a bit counter-intuitive that we builtÂ Cortex, our open source ML infrastructure platform, primarily for software engineers.
Going all the way back to machine learningâ€™s roots in the 1950s, the field has historically been research-focusedâ€”things like Arthur Samuelâ€™s checkers-playing AI (1959) or IBMâ€™s chess-playing Deep Blue (1988).
Starting around 2010, there was a renewed interest in deep learning, with major tech companies releasing breakthroughs. Projects like Google Brain, DeepMind, and OpenAI (among others) began publishing new, state-of-the-art results.
These breakthroughs manifested as features in big companiesâ€™ products:
- Netflixâ€™s recommendation engine
- Gmailâ€™s smart compose
- Facebookâ€™s facial recognition tags
In addition, this renewed focus on machine learningâ€”and particularly deep learningâ€”lead to the creation of better tools and frameworks, like Googleâ€™s TensorFlow and Facebookâ€™s PyTorch, as well as open source models and datasets, like OpenAIâ€™s GPT-2 and ImageNet.
With better tools, open source models, and accessible data, it became possible for small teams to train models for production. As a consequence of this democratization, a wave of new products have emerged, all of which at their core are â€œjustâ€ ML models wrapped in software. We refer to these products as ML-native.
This article briefly outlines how as Machine Learning (ML) becomes more a part of corporate solutions, the need for MLOps is going to become more critical.
The termÂ MLOpsÂ refers to a set of techniques and practises for data scientists to collaborate operations professionals.. MLOps aims to manage deployment of machine learning and deep learning models in large-scale production environments.
The termÂ DevOpsÂ comes from the software engineering world and is concerned with developing and operating large-scale software systems.Â DevOps introduces two concepts:Â Continuous Integration (CI) and Continuous Delivery (CD).Â DevOps aims to shorten development cycles, increase deployment velocity and create dependable releases.
This post explores while tinyML may be the next big thing.
A coalescence of several trends has made the microcontroller not just a conduit for implementing IoT applications but also a powerful, independent processing mechanism in its own right. In recent years, hardware advancements have made it possible for microcontrollers to perform calculations much faster.Â Improved hardware coupled with more efficient development standards have made itÂ easier for developersÂ toÂ build programs on these devices. Perhaps the most important trend, though, has been the rise of tiny machine learning, or TinyML. Itâ€™s a technology weâ€™ve been following since investing in a startup in this space.
TinyML broadly encapsulates the field of machine learning technologies capable of performing on-device analytics of sensor data at extremely low power. Between hardware advancements and the TinyML communityâ€™s recent innovations in machine learning, it is now possible to run increasingly complexÂ deep learningÂ models (the foundation of most modern artificial intelligence applications) directly on microcontrollers. A quick glance under the hood shows this is fundamentally possible because deep learning models are compute-bound, meaning their efficiency is limited by the time it takes to complete a large number of arithmetic operations. Advancements in TinyML have made it possible toÂ run these models on existing microcontroller hardware.
In other words, those 250 billion microcontrollers in our printers, TVs, cars, and pacemakers can now perform tasks that previously only our computers and smartphones could handle. All of our devices and appliances are getting smarter thanks to microcontrollers.
TinyML represents a collaborative effort between the embedded ultra-low power systems and machine learning communities, which traditionally have operated largely independently. This union has opened the floodgates for new and exciting applications of on-device machine learning. However, the knowledge that deep learning and microcontrollers are a perfect match has been pretty exclusive, hidden behind the walls of tech giants like Google and Apple. This becomes more obvious when you learn that this paradigm of running modified deep learning models on microcontrollers is responsible for the â€œOkay Googleâ€ and â€œHey Siri,â€ functionality that has been around for years.
But why is it important that we be able to run these models on microcontrollers? Much of the sensor data generated today is discarded because of cost, bandwidth, or power constraints â€“ or sometimes a combination of all three. For example, take an imagery micro-satellite. Such satellites are equipped with cameras capable of capturing high resolution images but are limited by the size and number of photos they can store and how often they can transmit those photos to Earth. As a result, such satellites have to store images at low resolution and at a low frame rate. What if we could use image detection models to save high resolution photos only if an object of interest (like a ship or weather pattern) was present in the image? While the computing resources on these micro-satellites have historically been too small to support image detection deep learning models, TinyML now makes this possible.