Machine learning
Recent articles
The Transmitter’s favorite essays of 2025
Throughout a tumultuous year in science, researchers opined on policy changes and funding uncertainty, as well as scientific trends and the impact of artificial-intelligence tools on the field.
The Transmitter’s favorite essays of 2025
Throughout a tumultuous year in science, researchers opined on policy changes and funding uncertainty, as well as scientific trends and the impact of artificial-intelligence tools on the field.
Exclusive: Springer Nature retracts, removes nearly 40 publications that trained neural networks on ‘bonkers’ dataset
The dataset contains images of children’s faces downloaded from websites about autism, which sparked concerns at Springer Nature about consent and reliability.
Exclusive: Springer Nature retracts, removes nearly 40 publications that trained neural networks on ‘bonkers’ dataset
The dataset contains images of children’s faces downloaded from websites about autism, which sparked concerns at Springer Nature about consent and reliability.
Beyond the algorithmic oracle: Rethinking machine learning in behavioral neuroscience
Machine learning should not be a replacement for human judgment but rather help us embrace the various assumptions and interpretations that shape behavioral research.
Beyond the algorithmic oracle: Rethinking machine learning in behavioral neuroscience
Machine learning should not be a replacement for human judgment but rather help us embrace the various assumptions and interpretations that shape behavioral research.
What are the fastest-growing areas in neuroscience?
Respondents pointed to computational neuroscience, systems neuroscience, neuroimmunology and neuroimaging, among other subfields.
What are the fastest-growing areas in neuroscience?
Respondents pointed to computational neuroscience, systems neuroscience, neuroimmunology and neuroimaging, among other subfields.
What are the most transformative neuroscience tools and technologies developed in the past five years?
Artificial intelligence and deep-learning methods featured prominently in the survey responses, followed by genetic tools to control circuits, advanced neuroimaging, transcriptomics and various approaches to record brain activity and behavior.
What are the most transformative neuroscience tools and technologies developed in the past five years?
Artificial intelligence and deep-learning methods featured prominently in the survey responses, followed by genetic tools to control circuits, advanced neuroimaging, transcriptomics and various approaches to record brain activity and behavior.
How neuroscientists are using AI
Eight researchers explain how they are using large language models to analyze the literature, brainstorm hypotheses and interact with complex datasets.
How neuroscientists are using AI
Eight researchers explain how they are using large language models to analyze the literature, brainstorm hypotheses and interact with complex datasets.
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.
Explore more from The Transmitter
How to collaborate with AI
To make the best use of LLMs in research, turn your scientific question into a set of concrete, checkable proposals, wire up an automatic scoring loop, and let the AI iterate.
How to collaborate with AI
To make the best use of LLMs in research, turn your scientific question into a set of concrete, checkable proposals, wire up an automatic scoring loop, and let the AI iterate.
How artificial agents can help us understand social recognition
Neuroscience is chasing the complexity of social behavior, yet we have not answered the simplest question in the chain: How does a brain know “who is who”? Emerging multi-agent artificial intelligence may help accelerate our understanding of this fundamental computation.
How artificial agents can help us understand social recognition
Neuroscience is chasing the complexity of social behavior, yet we have not answered the simplest question in the chain: How does a brain know “who is who”? Emerging multi-agent artificial intelligence may help accelerate our understanding of this fundamental computation.
Methodological flaw may upend network mapping tool
The lesion network mapping method, used to identify disease-specific brain networks for clinical stimulation, produces a nearly identical network map for any given condition, according to a new study.
Methodological flaw may upend network mapping tool
The lesion network mapping method, used to identify disease-specific brain networks for clinical stimulation, produces a nearly identical network map for any given condition, according to a new study.