Hector Garcia Rodriguez

I am a research engineer at Huawei Technologies, where I do research on efficient deep learning.

I graduated with an MSc Machine Learning from University College London, where I was advised by Timoleon Moraitis and Pontus Stenetorp during my dissertation "A new recurrent unit with synaptic short-term plasticity". I was included in the Dean's List (Top 5%) and awarded a Distiction. Previously, I interned as a Software Development Engineer in Amazon Web Services, and obtained a BSc Theoretical Physics from University College London with First Class Honours.

LinkedIn  /  Twitter  /  Github

I'm interested in multimodal representation learning: improving efficiency and reliability using adaptable networks with adjustable compute budgets, and using more contextualised representations for sequential decision making tasks.

We train deep ConvNets with an unsupervised Hebbian soft winner-take-all algorithm, multilayer SoftHebb. It sets SOTA results in image classification in CIFAR-10, STL-10 and ImageNet for other biologically plausible networks. SoftHebb increases biological compatibility, parallelisation and performance of state-of-the-art bio-plausible learning.

STPN is a recurrent neural network that improves Supervised and Reinforcement Learning by meta-learning to adapt its weights to the recent context, inspired by computational neuroscience. Additionally, STPN shows higher energy efficiency in a simulated neuromorphic implementation, due to its optimised explicit forgetting mechanism.

Template