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
Neural Networks with Binary Weights and Activations at Runtime
We analyze stonk price patterns in order to predict future price gyrations in a volatile and unpredictable global market (2021-?)
A regularization method for ViT. Works surprisingly well on small scale datasets!
The goal of this project is to put the paper "End-to-End Object Detection of Transformers" into practice.
Captioning and classifying architectural images
Determining using satellite radar data whether an object in the water is a ship or an iceberg
We are exploring VAEs for generating realistic music clips.
Finding an optimization strategy to play the game called Jstris, a game is an adaptation of tetris with some additional rules such as an ability to attack other players or techniques such as T-spin.
An Unsupervised Approach to a Chatbot
Deep Learning model that seeks to provide investors with a list of cryptocurrencies along with their predicted future trajectories.
Creating a model that classifies resistors to their resistance value based on their color bands
Our plan is to produce an eloquent, sparking conversationalist of a chatbot to replace the antiquated concept of 'human friends'.
Captioning images using a CNN and Transformers
Reinforcement learning is an important tool for models to adapt to their environments. This project implements graph convolution reinforcement learning as a solution to produce cooperative agents.
A conversational chatbot that can detect the user’s emotions and respond accordingly
Reimplementation of the NEAT Paper
In this project, we want to utilize the ability of deep learning with object detection that involves identifying traffic lanes in digital photographs.
Our project idea is music style transfer. The goal is to create a model that can take in as input a song from one genre of music and output the same song in a different genre.
Using Graph Convolutional Networks for Single-Cell Classification
generative adversarial network that generates plausible images of objects from detailed text descriptions.
Using deep learning to detect anomalies in system logs.
An Incremental Approach to Dense Semantic Correspondence
Predict stock prices using different CNN-LSTM type networks, refined using weather data of specific regions and companies.
Detect fakes from the dataset containing real images and CNN-augmented images.
73 – 96 of 120
