Our vision is to build upon growing technologies and research by translating theory into meaningful projects. With self-learning software at the frontier of technology, we can solve relevant problems through our intelligent projects. Check out how we are applying powerful algorithms to build production-ready systems.
Every semester, our project leaders look for challenging problems to tackle with state of the art techniques. Each team dives deep into their respective fields and designs creative solutions to solve the problem.
We also work closely with industry leaders to develop machine learning solutions. We are always looking for companies to work with us! Check out our industry page for more information.
Develop an intelligent Mario Kart agent that can replicate the skill and technique of a human player using behavior cloning algorithms
Converting rap lyrics to Shakespearian-style text using Transformers and RNNs. The 1500's never looked so dope.
Creating high-quality 3D reconstructions from photos of our own. Each member will choose variable scenes and items to reconstruct with NeRF and various follow up methods.
Experiment with a VQ-VAE based network for converting audio to the style of another audio file
Create a voice conversion model framework for voice assistants, implementing data generation, spectral analysis, and an Amazon Lex-based web app
Artificially stain various cellular samples using cutting edge style transfer techniques
Build a production ready virtual assistant chatbot with robust machine learning pipelines and slack integration
Enable semantic search through images and other mediums in a zero-shot manner with CLIP
Few-shot meta learning to learn handwriting styles and generate similar handwritten text using GANs
Experiment on multi-agent reinforcement learning for playing the popular sport, soccer
Apply Computer Vision techniques to improve tiny object detection on measuring roof debris and damage
Build an encoder for images that can perform few-shot training across CV tasks using unsupervised learning
Explore adversarial models to track sleep stages by comparing results from watch and radio frequency data to brain wave data
Develop a profitable trading strategy for the market today based on common technical indicators
Create an AI web app using Monte Carlo sampling, deep and reinforcement learning to play heads up and nine handed no-limit Texas Hold'em poker
A pictionary-like web game with a bot to generate and classify sketches
Building models that detect, contextualize, and identify relationships between humans and objects in images.
A web app where users can upload pictures from their photo album and generate ambient sounds and songs from the image’s scenery and emotion
Merging information between multiple cameras to track objects of interest accurately in 3D spaces
Training state of the art reinforcement learning agents to play the popular game, Super Smash Bros Melee
Animal information and tracking using a CNN with Raspberry Pi to send information to the cloud
Reinforcement learning in competitive environments for simulating intelligence
Universal codebook for image compression using evolutionary-based optimization methods
Fake news detecting Chrome extension incorporating NLP techniques and stance detections
Converting music between different styles/instrumentations using encoder-decoder networks in PyTorch
Post-workout image generation using generative adversarial networks
NBA playoff performance prediction from regular season data using statistical learning and neural networks
Weather forecasting using high-resolution video frame prediction using CNNs and RNNs
Answering visual questions using image and word embeddings and recurrent attention algorithms
Beautifying Berkeley with a #filter created with CycleGAN, an image to image translation neural network
Stock market trend prediction using NLP and time series analysis
Improving existing convolutional neural network architecture for real-time low-light image inferencing
Generative models for reinforcement learning to attain high performance with simplicity
Analyzing exploration and curiosity-based techniques in deep reinforcement learning
Food image generation using generative adversarial networks
Detecting and responding to dangerous driving situation by predicting collisions and road closures
Predicting driver behavior to improve rider experience in autonomous vehicles using kinematics and LSTMs
Multi-Objective Robotics solution for efficient and adaptive robot operation
Meta learning and multi-task learning
Augmenting low-fidelity images of 2D faces using 3D facial reconstruction
Generating jazz melodies in specified styles using Markov chains and clustering
Polyphonic music generation using deep neural networks
Building a human-centric computer vision API that provides optimized algorithms for object detection and tracking
Voice controlled computers using natural language processing