Diana Mosquera's repositories
dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
copilot-docs
Documentation for GitHub Copilot
library
a library of easily downloadable datasets with animal vocalizations (audio)
AwesomeAnimeResearch
Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.
Decoding-of-Motor-Responses-from-Neural-Population-Activity-in-Mice
We will try to understand which areas of the brain are involved in the behavior of the mice during the experimental task of the Steinmetz dataset recorded using Neuropixel probes. For this approach we will try to use a machine learning model to classify the different responses the mice made. We’ll use recordings from different brain regions as inputs to study the brain activity specific to different decision-making tasks in mice. And we will evaluate different time-window sizes of the recording to use as input of the model. We will apply Dimensionality Reduction on the data of different brain regions, train a classification model of the rat's response and explain the impact of different brain regions activity using SHAP additive explanations. Our analysis should help us understand dominant areas of the brain that are involved in the decision making process of the mice between the time zones stimulus onset and reaction time of the mice. The experimental task involves visual stimuli followed by an auditory cue that signals the mouse's movement of the wheel. If the movement of the wheel is correct the mouse receives a reward. Keywords: Steinmetz
course-content
Content for NMA Computational Neuroscience course
autoenconder
An autoencoder implementation on the wisconsin breast cancer dataset
jukebox
Code for the paper "Jukebox: A Generative Model for Music"
Twitter_Geolocation
Geolocating twitter users by the content of their tweets
clusterai_2021
Repository for the UTN BA Data Science Course 2020
steinmetz-et-al-2019
Code accompanying Steinmetz et al., 2019
mit-borderline-app
Augmented reality app for the Borderline Mural Project at MIT
deep-learning-project
this is some projects in which I have worked applying DL, all code is in python
Neural-Network
A neural network library, with training, query, and backquery functionality.
exercism-some-solutions
some solutions of exercism track python, r and Julia
Diana-M
Diana Mosquera