Mihaela Rosca

About me

I am a Research Engineer working at DeepMind. Previously I was working at Google in Zurich on NLP using neural networks.

Education

I finsihed my 4 year Computing MEng degree from Imperial College London in 2014, with first honours and a prize of excellence for an outstanding overall performance.

Professional Interests

Generative models, reinforcement learning, natural language processing, scalable and safe machine learning.

Papers and thesis

Variational Approaches for Auto-Encoding GANs
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
Distribution matching in variational inference
Learning Implicit Generative Models with the Method of Learned Moments
Sequence-to-sequence neural network models for transliteration
Networks with emotions, master thesis

Talks

VAE-GAN Hybrids at the GAN tutorial at CVPR 2018
The power and the promise of generative models
Unsupervised learning for building intelligent systems
Autoencoder GAN talk at GAN workshop at ICCV 2017
TensorFlow talk at the Deep Learning, Tools and Methods workshop
TensorFlow talk at DevFest 2016
TensorFlow meetups in London and Madrid

Open source projects

High performance GPU implementation of deep belief networks to assess their performance on facial emotion recognition from images. Github
Hopfield networks and RBM implementation in Haskell. Github
Autolock - face detection based screen locking software Github

Misc

I was a lab assistant at TMLSS, teaching vision, autoregressive text models and latent variable image models.
Website for the GAN tutorial at ICCV 2017 that I co-organized with Ian Goodfellow.
Some of my machine learning notes