Neural networks with biologically-inspired neural dynamics applied for drone-based tracking
Neural networks are the key technology of artificial intelligence that has led to breakthroughs in many important applications. These were achieved primarily by artificial neural networks that are loosely inspired by the structure of the brain, comprising neurons interconnected by synapses. Meanwhile, the neuroscientific community has developed the Spiking Neural Network (SNN) model that additionally incorporates biologically realistic temporal dynamics in the neuron structure. Although ANNs achieve impressive results, there is a significant gap in terms of power efficiency between biological brains and deep ANNs, which limits their widespread applicability for battery-powered devices at the edge, such as drones. One promising avenue to reduce this efficiency gap is to incorporate biologically-inspired dynamics mechanisms into common deep-learning architectures. Recently, the IBM team has demonstrated a new type of ANN unit, called a Spiking Neural Unit (SNU), that enables us to incorporate the SNN dynamics directly into deep ANNs. Our results demonstrate competitive performance, surpassing state-of-the-art RNNs, LSTM- and GRU-based networks.
In this Master’s thesis project, we aim to apply SNUs for tracking objects from a flying drone. A neuromorphic event-based camera will be mounted on a drone flying over objects emitting flashes of light, whose relative movement is determined through optical flow calculation in an SNN and is used for asset tracking purposes. The SNN architecture will be implemented and trained using Spiking Neural Units (SNUs) and IBM’s NeuroAI Toolkit. In particular, the project involves implementing the SNN operation in form of an executable on a neuromorphic chip to efficiently compute the optical flow. The work will build on the team’s prior experience with software simulations of a drone and IBM will provide extensive scientific guidance.
- Strong programming skills in Python.
- Experience with TensorFlow machine-learning framework.
- Strong analytical and problem-solving skills.
- Excellent communication and team skills.
IBM is committed to diversity at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.
How to apply
If you are interested in this exciting position, please submit your most recent curriculum vitae, your diplomas, as well as a motivational letter.
For technical questions, please contact:
Dr. Thomas Bohnstingl, firstname.lastname@example.org
Dr. Angeliki Pantazi email@example.com