Active Learning in DeepRod for Granular Behavioral Phenotypes

Our paper,“Active Learning in DeepRod Enables Efficient Discovery of Granular Behavioral Phenotypes,”was published in *Current Research in Behavioral Sciences *.
What is the biggest struggle in applied ML research today? Validating methods in a way that shows real-life impact, not just significant metrics on benchmarks. In healthcare and drug development this is critical. We want the AI solution that doesn't just win benchmarks but actually helps patients, and we see that from the real outcomes: better survival rates, earlier diagnoses, fewer compounds failing late in development, real pharmacological effect.
This is exactly what we highlight in our recently published paper on advanced active learning for automated behavioral analysis. We have a computer vision system that automates rodent behavioral phenotyping in pharmacological studies.
The bottleneck of manual annotation for studies generating 14–24 hours of video per animal is already solved by DeepRod's core module, which automatically predicts behaviors at each timepoint. However, automated models still require training data, and active learning is the core approach we use to minimize this initial labeling effort for model training.

Advanced active learning methods solve the annotation burden by selecting only the most informative samples for labeling. We didn't just show it improves classification accuracy, we showed that the model trained on just 0.5% of a full labeling set, still detects statistically significant drug-induced behavioral changes - the same effects the fully-trained reference model detects. Including fine-grained distinctions like Apathy versus Sleep under Clonidine treatment, which coarser methods collapse entirely.
None of this happens without the collaboration. Boehringer Ingelheim's scientists didn't just provide data, they defined what a meaningful result looks like in a preclinical setting. That domain knowledge shaped the method.
This is what we build at Merantix Momentum: ML that's validated against outcomes, not just benchmarks, built with the people who understand the domain well enough to define what outcomes matter.
Subscribe to the Merantix Momentum Newsletter now.
More articles
Active Learning in DeepRod for Granular Behavioral Phenotypes
Our paper,“Active Learning in DeepRod Enables Efficient Discovery of Granular Behavioral Phenotypes,”was published in *Current Research in Behavioral Sciences *.
What is the biggest struggle in applied ML research today? Validating methods in a way that shows real-life impact, not just significant metrics on benchmarks. In healthcare and drug development this is critical. We want the AI solution that doesn't just win benchmarks but actually helps patients, and we see that from the real outcomes: better survival rates, earlier diagnoses, fewer compounds failing late in development, real pharmacological effect.
This is exactly what we highlight in our recently published paper on advanced active learning for automated behavioral analysis. We have a computer vision system that automates rodent behavioral phenotyping in pharmacological studies.
The bottleneck of manual annotation for studies generating 14–24 hours of video per animal is already solved by DeepRod's core module, which automatically predicts behaviors at each timepoint. However, automated models still require training data, and active learning is the core approach we use to minimize this initial labeling effort for model training.

Advanced active learning methods solve the annotation burden by selecting only the most informative samples for labeling. We didn't just show it improves classification accuracy, we showed that the model trained on just 0.5% of a full labeling set, still detects statistically significant drug-induced behavioral changes - the same effects the fully-trained reference model detects. Including fine-grained distinctions like Apathy versus Sleep under Clonidine treatment, which coarser methods collapse entirely.
None of this happens without the collaboration. Boehringer Ingelheim's scientists didn't just provide data, they defined what a meaningful result looks like in a preclinical setting. That domain knowledge shaped the method.
This is what we build at Merantix Momentum: ML that's validated against outcomes, not just benchmarks, built with the people who understand the domain well enough to define what outcomes matter.
.png)

.png)

.png)
.png)
.png)

