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
We will be using recursive neural networks to detect and classify political ideologies.
Generate captions for instagram
Comparison between LSTM and attention model for image captioning
In this work, we propose an improved version of Cutout, which utilizes per-pixel importance scores created by a model interpretability method, Grad-CAM. We call this method Gutout.
In this project we will be implementing a Deep Learning Neural Network Algorithm to predict Twitter users’ political affiliations using a singular tweet.
Deep fake detection using deep learning
Traffic Sign Classification and Detection
Classifying fonts with neural network
Transfers the input sentences given from human users to some more structured and detailed paragraphs, which could enhance the performance of conversation generation of GPT-2.
Generating music with harmony and structure using RNNs trained on a classical music corpus.
Our 2020 DL Project
Speech Emotion Recognition Using Attention-Based Fully Convolutional Neural Network
Creating An Interpretable CNN Model for Audio
Using deep learning neural networks to classify wastes
Coloring black and white images!
Reinventing state of the art American Sign Language recognition
CSCI 2470 Final ProjectUse machine learning method to characterize the high speed link
Producing Some Cool Computer Generated Ghibli Tunes
A conversation model that incorporates human-like behaviors in its responses.
Emulating the brain using Prototypes and Exemplars
We will design a Deep Reinforcement Learning agent to automate stock trading.
Reimplementation (with creative free license) of a paper using a CNN-LSTM deep learning neural network to classify environmental (non-speech) sounds as hazardous or non-hazardous.
To examine the effectiveness of SOTA meta-learning algorithms on top of pre-trained language model (i.e. BERT) on natural language understanding tasks and further on multimodal tasks
Reinforcement Learning with Value Distributions
73 – 96 of 113
