Using DeepLabCut for 3D markerless pose estimation across species and behaviors

Nature Protocols, Journal Year: 2019, Volume and Issue: 14(7), P. 2152 - 2176

Published: June 21, 2019

Language: Английский

---

The Role of Variability in Motor Learning

Annual Review of Neuroscience, Journal Year: 2017, Volume and Issue: 40(1), P. 479 - 498

Published: May 10, 2017

Trial-to-trial variability in the execution of movements and motor skills is ubiquitous widely considered to be unwanted consequence a noisy nervous system. However, recent studies have suggested that may also feature how sensorimotor systems operate learn. This view, rooted reinforcement learning theory, equates with purposeful exploration space that, when coupled reinforcement, can drive learning. Here we review explore relationship between both humans animal models. We discuss neural circuit mechanisms underlie generation regulation consider implications this work has for our understanding

Language: Английский

---

Deep learning tools for the measurement of animal behavior in neuroscience

Current Opinion in Neurobiology, Journal Year: 2019, Volume and Issue: 60, P. 1 - 11

Published: Nov. 29, 2019

Language: Английский

---

Revealing the structure of pharmacobehavioral space through motion sequencing

Nature Neuroscience, Journal Year: 2020, Volume and Issue: 23(11), P. 1433 - 1443

Published: Sept. 21, 2020

Language: Английский

---

Measuring behavior across scales

BMC Biology, Journal Year: 2018, Volume and Issue: 16(1)

Published: Feb. 23, 2018

The need for high-throughput, precise, and meaningful methods measuring behavior has been amplified by our recent successes in manipulating neural circuitry. largest challenges associated with moving this direction, however, are not technical but instead conceptual: what numbers should one put on the movements an animal is performing (or performing)? In review, I will describe how theoretical data analytical ideas interfacing recently-developed computational experimental methodologies to answer these questions across a variety of contexts, length scales, time scales. attempt highlight commonalities between approaches areas where further advances necessary place same quantitative footing as other scientific fields.

Language: Английский

---

Unsupervised identification of the internal states that shape natural behavior

Nature Neuroscience, Journal Year: 2019, Volume and Issue: 22(12), P. 2040 - 2049

Published: Nov. 25, 2019

Language: Английский

---

Algorithms for Olfactory Search across Species

Journal of Neuroscience, Journal Year: 2018, Volume and Issue: 38(44), P. 9383 - 9389

Published: Oct. 31, 2018

Localizing the sources of stimuli is essential. Most organisms cannot eat, mate, or escape without knowing where relevant originate. For many, if not most, animals, olfaction plays an essential role in search. While microorganismal chemotaxis relatively well understood, larger animals algorithms and mechanisms olfactory search remain mysterious. In this symposium, we will present recent advances our understanding flies rodents. Despite their different sizes behaviors, both species must solve similar problems, including meeting challenges turbulent airflow, sampling environment to optimize information, incorporating odor information into broader navigational systems.

Language: Английский

---

DeepEthogram, a machine learning pipeline for supervised behavior classification from raw pixels

eLife, Journal Year: 2021, Volume and Issue: 10

Published: Sept. 2, 2021

Videos of animal behavior are used to quantify researcher-defined behaviors interest study neural function, gene mutations, and pharmacological therapies. Behaviors often scored manually, which is time-consuming, limited few behaviors, variable across researchers. We created DeepEthogram: software that uses supervised machine learning convert raw video pixels into an ethogram, the present in each frame. DeepEthogram designed be general-purpose applicable species, video-recording hardware. It convolutional networks compute motion, extract features from motion images, classify behaviors. classified with above 90% accuracy on single frames videos mice flies, matching expert-level human performance. accurately predicts rare requires little training data, generalizes subjects. A graphical interface allows beginning-to-end analysis without end-user programming. DeepEthogram's rapid, automatic, reproducible labeling may accelerate enhance analysis. Code available at: https://github.com/jbohnslav/deepethogram.

Language: Английский

---

Simple Behavioral Analysis (SimBA) as a platform for explainable machine learning in behavioral neuroscience

Nature Neuroscience, Journal Year: 2024, Volume and Issue: 27(7), P. 1411 - 1424

Published: May 22, 2024

Language: Английский

---

Recognizing Diverse Construction Activities in Site Images via Relevance Networks of Construction-Related Objects Detected by Convolutional Neural Networks

Journal of Computing in Civil Engineering, Journal Year: 2018, Volume and Issue: 32(3)

Published: Feb. 16, 2018

Timely and overall knowledge of the states resource allocation diverse activities on construction sites is critical to leveling, progress tracking, productivity analysis. Despite its importance, this task still performed manually. Previous studies have taken a significant step forward in introducing computer vision technologies, although they been oriented toward limited classes objects or types activities. Furthermore, especially focus single activity recognition, where an image contains only execution by one few objects. This paper introduces two-step method for recognizing site images. It detects 22 construction-related using convolutional neural networks. With detected, semantic relevance representing likelihood cooperation coexistence between two activity, spatial two-dimensional pixel proximity coordinates, patterns are defined recognize 17 The advantage proposed potential concurrent fully automatic way. Therefore, it possible save managers' valuable time manual data collection concentrate their attention solving problems that necessarily demand expertise.

Language: Английский

---