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
|
|
Research
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.
|
|
Hebbian Deep Learning Without Feedback
Adrien Journé,
Hector Garcia Rodriguez,
Qinghai Guo,
Timoleon Moraitis
ICLR notable-top-25% (spotlight), 2023
arXiv /
code /
talk
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.
|
|