External links

LEDNeCo: Low Energy Deep Neurocomputing

Standard - GACR GA25-15490S [Registered results] 2025 - 2027

Principal Investigator: doc. RNDr. Jiří Šíma, DrSc.

The aim of the LEDNeCo project is to develop a low-energy deep neurocomputing paradigm based on machine-independent energy complexity theory of deep neural network models, which will be applied in new advanced techniques for the design of their hardware accelerators with the low-energy consumption.

Modern artificial intelligence technologies based on deep neural networks (DNNs) such as GPT are computationally extremely demanding. In addition to consuming an enormous amount of energy, this limits their deployment in battery-powered embedded (edge) devices (e.g. smart mobile apps).

LEDNeCo is a project of basic research whose ambition is to develop a low-energy deep neurocomputing paradigm based on machine-independent energy complexity theory for DNNs, which issues from practical experience in the design of diverse DNN hardware accelerators. Among other things, universal lower bounds on energy complexity of DNNs and estimates of inference error will be derived for identifying DNN components (e.g. weights, neurons, layers) whose approximation is provably the most energy efficient.

The achieved theoretical knowledge will be used in new advanced approximation techniques (e.g. weight compression, Boolean optimization, robust aproximation of components) for low-power hardware implementations of DNN (incl. transformers), which will be tested on benchmark datasets.