I like how [author-Grace-Lindsay] describes her research programme, same as how [author-Anna-Ivanova] does. I think I will try to do the same here.

[author-Grace-Lindsay] describes her research programme as:

RESEARCH DIRECTIONS

Understanding Attention

Attention is widely studied across psychology, neuroscience, and machine learning. To what extent do these different forms of attention relate to each other? Can we use models of attention in artificial neural networks to understand how attention enhances behavior in people? What can the connection between attention and learning in biology tell us about how to make machines learn better?

Read “Attention in Psychology, Neuroscience, and Machine Learning”

Investigating the Tools of Neuroscience

Neuroscientists use a variety of analysis methods to try to identify the features of neural activity that drive behavior. Are these tools capable of providing such insights? Artificial neural networks offer an ideal testing ground for the tools of neuroscience as they allow for full access to the neural activity responsible for behavior.

Read “Testing the Tools of Systems Neuroscience on Artificial Neural Networks”


Machine Learning for Climate Change

Mitigating and adapting to climate change is the biggest challenge of our generation. Progress in many areas can be expedited through the use of artificial intelligence. The Lindsay Lab is particularly focused on analysis of remote sensing data.

Learn more about why the lab works on climate change

Moreover, [author-Anna-Ivanova] describes her research programme as:

Meaning in the brain
How does the human brain store and operate over conceptual knowledge? Is knowledge domain-specific or domain-general? Does the brain have dedicated machinery for navigating the conceptual space? What is the role of the language brain network in semantic/conceptual processing?

Meaning in large language models
What aspects of world knowledge are learnable from distributional patterns in text? Do large language models have robust internal models of objects, agents, properties, and events in the world? Do models operate over world knowledge representations in a way similar to humans?

Inner speech & thought
How can we measure people's subjective experiences of inner speech imagery? Do inner speech experiences mediate behavioral performance and neural activity evoked by diverse cognitive tasks? Can we predict how strongly a person relies on inner speech from brain activity alone? And can inner speech support reasoning in AI systems?

Methods matter
How can we leverage the synergy between neuroscience and AI to design better methods for probing and interpreting intelligent systems? What is the optimal tradeoff between simplicity and fidelity when designing neural probes? Can we use the power of flexible new tools like Julia to develop better analysis practices?

Who am I?

In a sense [you-research-what-strikes-you-deeply], so who am I then. I think I will put here the numerous descriptions I have used to try to organize my thoughts.

Exhibit A - My github description

As a researcher I'm interested in :

- Anything-Inspired Models & AI
- Cognitive-Neuro-Complexity Science
- Methods rather than Topics
- Explainability and Interpretability
- Representation and Visceralization
- Complex Systems Modeling & Analysis

Exhibit B - My cv description

Passionate about understanding natural and artificial intelligence, as well as the models and algorithms they encapsulate. I like to think critically about cognitive representations, model interpretability and explainability, data and knowledge representation and visceralization, the relation between form and function, the methods and perspectives we use to reverse engineer and think about cognitive entities, and in general, how and why cognitive systems arise, work and came to be. I’m enraptured by systems, complexity, curious dynamics and emergence. Amateur musician, occasional poet, chaotic dancer, wannabe mathematician and dabbler algorithmic artist. My work is built upon the values of responsibility, commitment, honesty, attention to detail, problem solving and critical thinking.