mindtrace.ai

mindtrace.ai is rated 3 out of 5 in the category making machines think. Read and write reviews about mindtrace.ai. Mindtrace aims at revolutionising the world of Artificial Intelligence. Using inspiration from the brain, our goal is to develop novel and unique neuromorphic algorithms, sensors and processing hardware, to create machines which are able to continuously and autonomously learn about the real world, and use this knowledge for predictive decision making. Our systems will seamlessly integrate learning in deep neural networks with inference over distributed graph-based knowledge representations to facilitate continuous "one-shot"​ learning and inference and the transfer of learnt knowledge to new domains. Our neuromorphic machine learning and inference algorithms are designed to be executed on massively parallel, many core distributed computer systems which exploit event-based, asynchronous, sparse computation for speed, efficiency and low energy. Using event-based vision sensors, together with our neuromorphic algorithms and processing hardware, we are building end-to-end asynchronous event based low energy machine vision systems, which use our unique STAR technology to provide fast, dynamic Selection, Tracking And Recognition of anomalous motion events of interest, for deployment in areas such as ADAS, robotics, security and surveillance, “What we see changes what we know. What we know changes what we see.” ― Jean Piaget