Machine learning
Recent articles
Competition seeks new algorithms to classify social behavior in animals
The winner of the competition, which launched today and tests contestants’ models head to head, is set to take home $20,000, according to co-organizer Ann Kennedy.

Competition seeks new algorithms to classify social behavior in animals
The winner of the competition, which launched today and tests contestants’ models head to head, is set to take home $20,000, according to co-organizer Ann Kennedy.
This paper changed my life: Dan Goodman on a paper that reignited the field of spiking neural networks
Friedemann Zenke’s 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks. The innovation reinvigorated the field.

This paper changed my life: Dan Goodman on a paper that reignited the field of spiking neural networks
Friedemann Zenke’s 2019 paper, and its related coding tutorial SpyTorch, made it possible to apply modern machine learning to spiking neural networks. The innovation reinvigorated the field.
Xaq Pitkow shares his principles for studying cognition in our imperfect brains and bodies
Pitkow discusses how evolution's messy constraints shape optimal brain algorithms, from Bayesian inference to ecological affordances.
Xaq Pitkow shares his principles for studying cognition in our imperfect brains and bodies
Pitkow discusses how evolution's messy constraints shape optimal brain algorithms, from Bayesian inference to ecological affordances.
Should neuroscientists ‘vibe code’?
Researchers are developing software entirely through natural language conversations with advanced large language models. The trend is transforming how research gets done—but it also presents new challenges for evaluating the outcomes.

Should neuroscientists ‘vibe code’?
Researchers are developing software entirely through natural language conversations with advanced large language models. The trend is transforming how research gets done—but it also presents new challenges for evaluating the outcomes.
Breaking the jar: Why NeuroAI needs embodiment
Brain function is inexorably shaped by the body. Embracing this fact will benefit computational models of real brain function, as well as the design of artificial neural networks.

Breaking the jar: Why NeuroAI needs embodiment
Brain function is inexorably shaped by the body. Embracing this fact will benefit computational models of real brain function, as well as the design of artificial neural networks.
Many students want to learn to use artificial intelligence responsibly. But their professors are struggling to meet that need.
Effectively teaching students how to employ AI in their writing assignments requires clear guidelines—and detailed, case-specific examples.

Many students want to learn to use artificial intelligence responsibly. But their professors are struggling to meet that need.
Effectively teaching students how to employ AI in their writing assignments requires clear guidelines—and detailed, case-specific examples.
The BabyLM Challenge: In search of more efficient learning algorithms, researchers look to infants
A competition that trains language models on relatively small datasets of words, closer in size to what a child hears up to age 13, seeks solutions to some of the major challenges of today’s large language models.

The BabyLM Challenge: In search of more efficient learning algorithms, researchers look to infants
A competition that trains language models on relatively small datasets of words, closer in size to what a child hears up to age 13, seeks solutions to some of the major challenges of today’s large language models.
Connectomics 2.0: Simulating the brain
With a complete fly connectome in hand, researchers are taking the next step to model how brain circuits fuel function.

Connectomics 2.0: Simulating the brain
With a complete fly connectome in hand, researchers are taking the next step to model how brain circuits fuel function.
Dean Buonomano explores the concept of time in neuroscience and physics
He outlines why he thinks integrated information theory is unscientific and discusses how timing is a fundamental computation in brains.
Dean Buonomano explores the concept of time in neuroscience and physics
He outlines why he thinks integrated information theory is unscientific and discusses how timing is a fundamental computation in brains.
Basic pain research ‘is not working’: Q&A with Steven Prescott and Stéphanie Ratté
Prescott and Ratté critique the clinical relevance of preclinical studies in the field and highlight areas for improvement.

Basic pain research ‘is not working’: Q&A with Steven Prescott and Stéphanie Ratté
Prescott and Ratté critique the clinical relevance of preclinical studies in the field and highlight areas for improvement.
Explore more from The Transmitter
ADSI, leucovorin, autism registry; and more
Here is a roundup of autism-related news and research spotted around the web for the week of 6 October.

ADSI, leucovorin, autism registry; and more
Here is a roundup of autism-related news and research spotted around the web for the week of 6 October.
One year of FlyWire: How the resource is redefining Drosophila research
We asked nine neuroscientists how they are using FlyWire data in their labs, how the connectome has transformed the field and what new tools they would like to see in the future.

One year of FlyWire: How the resource is redefining Drosophila research
We asked nine neuroscientists how they are using FlyWire data in their labs, how the connectome has transformed the field and what new tools they would like to see in the future.
Neurons fuel lung tumors that have spread to brain
Functional synapses between brain cells and cancer cells are key to the metastatic growth, according to new findings from two independent teams.

Neurons fuel lung tumors that have spread to brain
Functional synapses between brain cells and cancer cells are key to the metastatic growth, according to new findings from two independent teams.