Meet Microsoft’s ‘Bonsai Brain’: A Low-Code AI Platform That Speeds AI-Powered Automation Development

Microsoft’s recent ongoing project called Bonsai Brain is dedicated to modeling and creating a low-code-based AI component that can be applied to various autonomous tasks and applications. The brain of Bonsai has been trained and practiced to manage unforeseen scenarios and maintain operations. Its key selling feature is the significant decrease in downtime resulting from improved production efficiency. More extensive neural networks must be developed for automation tasks, but Bonsai’s brain functions without trained or emulated neural networks. Users can build their own bespoke AI models using the interface of the Bonsai brain and implement them appropriately without needing additional resources.

To simulate and train the Bonsai brain for all unpredictable conditions and to ensure that wiser Autonomous systems are developed, the Bonsai brain platform essentially leverages deep reinforcement learning concepts. Three guiding principles govern how the Bonsai brain platform functions, with the Integrate component serving as the central tenet. This part is in charge of fusing training simulations for the Bonsai brain with actual circumstances and giving the training process appropriate feedback. By the input from the Integrate component, the second component, known as Train, is in charge of training and modeling the brain. The platform’s final export component is a fully trained and simulative Bonsai Brain that will be made accessible as a Linux container installed on-site or in the Azure environment. Two check conditions must be met to train the Bonsai brain in the platform. To ensure the Bonsai Brain is reliable and functioning as intended, the first criterion verifies that the precision for each simulated action must be exact. The second requirement assures that the likelihood of reversing a mistaken action taken by the brain must be high or quick.

Five essential elements form the basis of the entire bonsai brain. The agent in the Bonsai platform that will be trained and simulated to achieve the necessary goals is called the Brain. The second element of the Bonsai platform is the simulator, which simulates the brain to enable learning from various situations. Observations will be the simulator’s input, and the simulator’s output will be the various sets of actions that the Bonsai Brain in the Bonsai platform will carry out. One of the parts of the Bonsai platform, which houses all the Brains and simulators developed on the platform, is the workspace. One element of the Bonsai platform is iteration, which trains the brain to perform a particular action for each set of simulations. The platform’s brain, therefore, refers to each action as an iteration. The last part of the Bonsai platform, called Episode, is utilized to establish a cutoff point for platform iterations. The model’s ability to mimic and train the Brain following industry standards and subject-matter expertise ensures that the Brain simulation maintains its robustness. This is one of its defining characteristics. It may be modeled to adapt to any required immediate production changeovers swiftly.

With the aid of Bonsai’s brain, Microsoft hopes to remove unnecessary code and implement effective and reliable AI models. The Bonsai brain employs deep reinforcement learning methods to create efficient AI models that quickly simulate and create reliable AI models. According to the researchers, once Bonsai’s brain is completed, it will be an essential component of many automation systems and be incorporated into many AI models.

References:

  • Documentation: https://docs.microsoft.com/en-us/bonsai/
  • https://docs.microsoft.com/en-us/bonsai/product/
  • https://docs.microsoft.com/en-us/bonsai/product/components/simulation

Khushboo Gupta is a consulting intern at MarktechPost. She is currently pursuing her B.Tech from the Indian Institute of Technology(IIT), Goa. She is passionate about the fields of Machine Learning, Natural Language Processing and Web Development. She enjoys learning more about the technical field by participating in several challenges.