You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# {% include icon.html icon="fa-solid fa-database" %}Open Datasets
6
+
7
+
We believe in open science and making our research data accessible to the broader scientific community. This page provides information about datasets we have made publicly available.
8
+
9
+
{% include section.html %}
10
+
11
+
## AJILE12: Long-term Naturalistic Human Intracranial Neural Recordings and Pose
12
+
13
+
AJILE12 (_Annotated Joints in Long-term Electrocorticography for 12 human participants_) is a multimodal human electrocorticography (ECoG) dataset recorded during passive clinical epilepsy monitoring. The dataset includes synchronized intracranial neural recordings and upper body pose trajectories across 55 semi-continuous days of naturalistic movements from 12 human participants.
14
+
15
+
{% capture text %}
16
+
17
+
### Publication
18
+
19
+
Peterson, S.M., Singh, S.H., Dichter, B. et al. AJILE12: Long-term naturalistic human intracranial neural recordings and pose. _Sci Data_**9**, 184 (2022). [https://doi.org/10.1038/s41597-022-01280-y](https://doi.org/10.1038/s41597-022-01280-y)
Copy file name to clipboardExpand all lines: research/index.md
+8-7Lines changed: 8 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,7 +7,9 @@ nav:
7
7
8
8
# {% include icon.html icon="fa-solid fa-microscope" %}Research
9
9
10
-
For a complete list of the lab's publications, see PI Rao's [Google Scholar page](https://scholar.google.com/citations?user=02nHF0gAAAAJ).
10
+
**{% include icon.html icon="fa-solid fa-graduation-cap" %}[Google Scholar](https://scholar.google.com/citations?user=02nHF0gAAAAJ)** - Complete list of the lab's publications.
11
+
12
+
**{% include icon.html icon="fa-solid fa-database" %}[ Open Datasets]({{ site.baseurl }}/research/data/)** - Access our open-source datasets and request data for your research.
11
13
12
14
## Computational Neuroscience
13
15
@@ -16,7 +18,7 @@ Computational neuroscience offers a new way to understand the brain by leveragin
16
18
{% capture text %}
17
19
18
20
- Predictive coding and Bayesian brain models
19
-
- Models for ehavior and cognition based on partially observable Markov decision processes (POMDPs)
21
+
- Models for ehavior and cognition based on partially observable Markov decision processes (POMDPs)
20
22
- Hierarchical recurrent neural networks implementing the above models
21
23
22
24
{% endcapture %}
@@ -25,14 +27,14 @@ Computational neuroscience offers a new way to understand the brain by leveragin
25
27
26
28
## Brain-Computer Interfaces
27
29
28
-
Brain-computer interfaces (BCIs) are devices that connect brains directly to computers. BCIs can both record from the brain ("read" the brain) and stimulate the brain ("write" the brain). BCIs be used to help those who have impairments due to injury or neurological conditions. For example, by recording electrical signals from the brain, a BCI (1) can decode these signals into intention, such as the intention to move, and (2) actuate this intention by performing some output, such as moving a prosthetic arm, or turning on a light. Our lab works closely with neuroscientists, neurosurgeons and patients to explore novel methods to improve BCI technology. Current research projects include:
30
+
Brain-computer interfaces (BCIs) are devices that connect brains directly to computers. BCIs can both record from the brain ("read" the brain) and stimulate the brain ("write" the brain). BCIs be used to help those who have impairments due to injury or neurological conditions. For example, by recording electrical signals from the brain, a BCI (1) can decode these signals into intention, such as the intention to move, and (2) actuate this intention by performing some output, such as moving a prosthetic arm, or turning on a light. Our lab works closely with neuroscientists, neurosurgeons and patients to explore novel methods to improve BCI technology. Current research projects include:
29
31
30
32
{% capture text %}
31
33
32
34
- Brain co-processors: This project utilizes artificial intelligence to adaptively deliver stimulation and compute control signals as a function of the brain's ongoing neural activity and external sensory signals.
33
35
- Naturalistic BCIs: This project uses deep learning methods to improve decoding of brain signals in naturalistic settings.
34
36
- Decoding pain and mood: This project seeks to identify neural biomarkers for pain and mood.
35
-
- Modeling electrical stimulation: This project models the effects of therapeutic electrical stimulation using AI and machine learning techniques, and uses these models for developing brain co-processors.
37
+
- Modeling electrical stimulation: This project models the effects of therapeutic electrical stimulation using AI and machine learning techniques, and uses these models for developing brain co-processors.
36
38
37
39
{% endcapture %}
38
40
@@ -47,13 +49,12 @@ Our lab focuses on developing neurally inspired AI algorithms that leverage insi
47
49
- Active Predictive Coding: Developing dynamic, hierarchical world models that learn to compose simple dynamics, enabling AI to tackle complex tasks in vision and navigation.
48
50
- Visual Reinforcement Learning for Grounded Decision-Making: Investigating how reinforcement learning (RL) agents perceive and interpret their environments when making decisions.
49
51
- Active Inference and Successor Representations for Navigation: Integrating active inference with successor representations to create more flexible and efficient navigation strategies.
50
-
- Using AI to analyze the Indus script and art
52
+
- Using AI to analyze the Indus script and art
51
53
{% endcapture %}
52
54
<!--
53
55
- Active Predictive Coding: Learning dynamic and hierarchical world models to compose simple dynamics and solve complex problems in vision and navigation.
54
56
- Visual Reinforcement Learning for grounded decision making: We try to answer what an RL agent is looking at, when taking decisions.
55
57
- Active Inference and Successor Representation for navigation.
56
58
- Using AI to analyze the Indus script and art -->
57
59
58
-
59
-
{% include feature.html image="images/research/apc2.png" link="projects" style="bare" text=text %}
60
+
{% include feature.html image="images/research/apc2.png" link="projects" style="bare" text=text %}
0 commit comments