Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
For our project, we are investigating racial bias in American media’s reporting of gun-violence-related incidents by analyzing Professor Pavlick’s gun violence database: http://gun-violence.org/.
Using the power of a generative adversarial network (GAN) trained on a public classical music dataset, we aim to create classical music that is not only listenable, but interesting and complex.
We utilized two models: a live-time play-by-play LSTM and a dense model that utilized player/team stats We closely model important features of data that we believe are domain specific to basketball.
Our group aims to make the process of poetry creation as easy as uploading a text image, and our model generates a beautiful poem based on it.
Simplifies the given English text input
“Inspired by Cher's DressMe from the iconic movie, "Clueless", we seek to implement a fashion-informed deep learning model geared toward outfit generation.
We will combine our knowledge of deep learning from this course and our background in reinforcement learning to create deep reinforcement learning models to solve the tasks in SC2 video game.
Using deep learning to generate captions for images.
We look to implement real-value non-volume preserving transformations (https://arxiv.org/pdf/1605.08803.pdf) to learn distribution parameters through maximum likelihood.
Build a Long short-term memory (LSTM) network model that can find and reveal the right poet given a part of a poem
Intelligently Unintelligent #learningdeeply
Never crash your whip ever again in GTA5
We are detecting suicidal intent in tweets using a time-aware transformer based model. This incorporates both the tweet itself and past history of a user's tweets.
Simulating pipe flow using convolution and auto encoders much more efficiently than FEM!
Training an image classifier without using labels by building a model that can generate labels needed for training from the images themselves!
Want to predict stocks? weather? traffic? Predict temporal datasets with our new Neural ODE - GRU-D architecture
Traffic Sign classification using a Convolutional Neural Network
Using Concept Activation Vectors to understand how deep learning models learn to classify images
We explore different deep learning architectures to segment DNA sequence with nucleotide-level resolution.
Automatically busting classical ciphers 👻
Eli Shea and Zach Huang
An implementation of Pix2Pix that creates facades from blueprints
Fingerprint recognition using deep learning!
Classifying brain tumor MRI images as their subtypes using different neural network architectures can reduce the need for invasive diagnostic procedures like brain biopsies.
49 – 72 of 120
