ΑΙhub.org
 

#NeurIPS2020 invited talks round-up: part three – causal learning and the genomic bottleneck


by
26 March 2021



share this:
NeurIPS logo

In this post we conclude our summaries of the NeurIPS invited talks from the 2020 meeting. In this final instalment, we cover the talks by Marloes Maathuis (ETH Zurich) and Anthony M Zador (Cold Spring Harbor Laboratory).

Marloes Maathuis: Causal learning

Marloes began her talk on causal learning with a simple example of the phenomenon known as Simpson’s paradox, in which a trend appears in several different groups of data but disappears or reverses when these groups are combined. She also talked about the importance of considering causality when making decisions based on such data.

simpson's paradox and causality
Slide from the introductory part of Marloes talk where she discussed Simpson’s paradox and causality.

Marloes went on to explain the difference between causal and non-causal questions. Non-causal questions are about predictions in the same system, for example, predicting the cancer rate among smokers. Causal questions, on the other hand, are about the mechanism behind the data or about predictions after an intervention to the system. For example, asking if smoking causes lung cancer, or predicting the spread of a virus epidemic after imposing new regulations.

Causal questions are ideally answered by randomised controlled experiments. However, sometimes it is not possible to carry out these experiments, so we need to estimate causal effects from observational data. Marloes described her research into determining methodology, using causal directed acyclic graphs (DAGs) to estimate such causal effects.

In the final part of her presentation, Marloes explained the methodology used when the causal graph is unknown. One possible approach is to hypothesize possible DAGs. Another approach is to learn the DAG from the data.

To find out more you can watch the talk in full here.


Anthony M Zador: The genomic bottleneck: a lesson from biology

Anthony spoke about the innate abilities that animals have and argued that most animal behaviour is not the result of clever learning algorithms, but is encoded in the genome. Specifically, animals are born with highly structured brain connectivity, which enables them to learn very rapidly. Examples of innate ability include birds making species-specific nests and beavers building dams. Having these abilities as innate provides an evolutionary advantage.

Innate structure - slide from Anthony Zador's talk
Slide from Anthony’s talk – innate structure provides an evolutionary advantage.

In the talk, Anthony outlined the number of parameters it takes to wire the brains of different creatures. For C elegans (a type of worm), the simplest animal studied, 302 neurons with 7000 synapses are needed. The genome of C elegans consists of about 200 million bits (where two bits make a nucleotide). These 200 million bits are easily enough to specify the precise wiring of 7000 synapses.

Compare this to a human brain: we have roughly 1011 neurons and 1014 synapses. It is estimated that it takes about 1015 bits to specify a human brain. However, our genome is only 109 bits. Anthony explained this missing factor of 106: the genome doesn’t specify every single synapse, rather, it specifies rules for wiring up the brain.

This led onto discussion of the notion that the wiring diagram needs to be compressed through a “genomic bottleneck”. The genomic bottleneck suggests a path toward AI architectures capable of rapid learning and in the final part of his talk, Anthony outlined some of the research that he is carrying out in this area.

Watch the talk here.




tags: ,


Lucy Smith is Senior Managing Editor for AIhub.
Lucy Smith is Senior Managing Editor for AIhub.




            AIhub is supported by:


Related posts :



Exploring counterfactuals in continuous-action reinforcement learning

  20 Jun 2025
Shuyang Dong writes about her work that will be presented at IJCAI 2025.

What is vibe coding? A computer scientist explains what it means to have AI write computer code − and what risks that can entail

  19 Jun 2025
Until recently, most computer code was written, at least originally, by human beings. But with the advent of GenAI, that has begun to change.

Gearing up for RoboCupJunior: Interview with Ana Patrícia Magalhães

  18 Jun 2025
We hear from the organiser of RoboCupJunior 2025 and find out how the preparations are going for the event.

Interview with Mahammed Kamruzzaman: Understanding and mitigating biases in large language models

  17 Jun 2025
Find out how Mahammed is investigating multiple facets of biases in LLMs.

Google’s SynthID is the latest tool for catching AI-made content. What is AI ‘watermarking’ and does it work?

  16 Jun 2025
Last month, Google announced SynthID Detector, a new tool to detect AI-generated content.

The Good Robot podcast: Symbiosis from bacteria to AI with N. Katherine Hayles

  13 Jun 2025
In this episode, Eleanor and Kerry talk to N. Katherine Hayles about her new book, and discuss how the biological concept of symbiosis can inform the relationships we have with AI.

Preparing for kick-off at RoboCup2025: an interview with General Chair Marco Simões

  12 Jun 2025
We caught up with Marco to find out what exciting events are in store at this year's RoboCup.

Graphic novel explains the environmental impact of AI

  11 Jun 2025
EPFL’s Center for Learning Sciences has released Utop’IA, an educational graphic novel that explores the environmental impact of artificial intelligence.



 

AIhub is supported by:






©2025.05 - Association for the Understanding of Artificial Intelligence


 












©2025.05 - Association for the Understanding of Artificial Intelligence