Neural style transfer is an optimization technique used to take two images—a content image and a style reference image (such as an artwork by a famous painter)—and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image.
Accelerate data mining and deep learning applications via Intel onapi. Provide sample code and examples in SJSU CMPE255 Data Mining class (https://catalog.sjsu.edu/preview_course_nopop.php?catoid=12&coid=58423) to demonstrate the importance of acceleration and use Intel OneAPI as one technological e
OSSDC Vision AI - a platform for live testing and developing of computer vision and artificial intelligence algorithms targeting robotics, home automation and autonomous vehicles
Gaia ML is a special free version of Procedural Worlds award winning Gaia Pro procedural landscape generation system with an embedded copy of the AI GameDev Toolkit that makes it easy to explore OpenVINO and Baraccuda in Unity 3D, and available on Canopy.
We propose the PLSSVM library, which efficiently brings SVMs to massively parallel accelerators. It implements the basic functionality of the most widely used SVM library, LIBSVM, and can target different hardware from various vendors by using our backends: OpenMP, CUDA, HIP, OpenCL, and SYCL.
Gavin AI is a project, created by Scot_Survivor (Joshua Shiells) & ShmarvDogg, which aims to have Englsih human like conversations through the use of AI and ML. Gavin works on the Transformer architecture however, Performer & FNet architectures are being investigated for better scaling.
we propose a multilingual ensemble-based model that can identify offensive content targeted against an individual (or group) in low resource Dravidian language. Our model is able to handle code-mixed data as well as instances where the script used is mixed (for instance, Tamil and Latin).
Leveraging Generative Adversarial Networks to create self-driving data at scale is crucial. By emphasizing a focus on DCGANs, I’m focusing on creating high-quality self-driving images that can be used to train and improve the performance of computer vision models.
Used Convolutional Neural Networks + Deep Learning algorithms to create a learned agent that can perform binary classification of malignant vs benign skin cancer.
Built an object + lane detection algorithm without the use of any sort of Deep Learning. Used SVMs, polynomial fitting algorithms, and a bird's eye view implementation of the world to create an easily implementable real-time algorithm.
This project was made for TKS AI Hackathon in October 2020. Focused on solving distracted driving accidents (causes >96% of all 1.35 million deaths) by leveraging artificial intelligence algorithms such as transfer learning + Convolutional Neural Networks
Social distancing is a method, primarily used to control the spread of contagious diseases like Covid-19, etc. Using Artificial Intelligence, I have developed a mechanism which distinguishes the people who are following social distancing, and those who are not following.
This is my quantum open-source foundation project on building a quantum variational classifier using a heart attack dataset. The purpose of this project was to help me gain insight into the actual construction of a quantum model, applied to real data.
The Main motto behind to build Rossie is to make Rossie available across all platforms. Rossie is an Open source Virtual Assistant Build Completely using Python Programming.
Not everyone understands sign language,this project aims to solve this by removing the need of having a person who understands sign language interpret every single sign.
The project employs the following key areas:
1. Computer vision.
2. Deep learning. [TensorFlow library]
