Natasha Jaques

Affective Computing
  • Research Assistant

PhD candidate working on Affective Machine Learning:  problems at the intersection of machine learning (ML), deep learning, emotion, mental health, and social interaction. I'm interested in methods that allow ML models to learn generalizable representations across a range data or tasks, including transfer learning, multi-task learning, and intrinsic motivation.  Recently, I've begun investigating how social and emotional inductive biases can improve generalization and learning. Experienced in traditional machine learning, deep learning, Bayesian methods, causal inference and reinforcement learning. 

My favourite past projects have included: 

- Developing intrinsic social motivation based on assessing causal influence between agents to encourage cooperation in multi-agent reinforcement learning (RL).

- Improving deep generative models by using human facial expression responses to samples from the model as a training signal.

 - Effectively combining supervised learning and RL to train generative sequence models.

- Using multi-task learning techniques to personalize machine learning models and imp… View full description

PhD candidate working on Affective Machine Learning:  problems at the intersection of machine learning (ML), deep learning, emotion, mental health, and social interaction. I'm interested in methods that allow ML models to learn generalizable representations across a range data or tasks, including transfer learning, multi-task learning, and intrinsic motivation.  Recently, I've begun investigating how social and emotional inductive biases can improve generalization and learning. Experienced in traditional machine learning, deep learning, Bayesian methods, causal inference and reinforcement learning. 

My favourite past projects have included: 

- Developing intrinsic social motivation based on assessing causal influence between agents to encourage cooperation in multi-agent reinforcement learning (RL).

- Improving deep generative models by using human facial expression responses to samples from the model as a training signal.

 - Effectively combining supervised learning and RL to train generative sequence models.

- Using multi-task learning techniques to personalize machine learning models and improve accuracy in predicting next day stress, happiness and health.