Home Artificial Intelligence Education

Artificial Intelligence Education

Understanding Holistic Scene with Panoptic

Real-world computer vision applications, such as self-driving cars and robotics, rely on two core tasks — instance segmentation and semantic segmentation. Instance segmentation identifies the class and...

Advanced Python Features Worth Knowing

By Ahmad Anis, Machine learning and Data Science Student.Photo by David Clode on Unsplash. In this article, I will discuss 3 important features of Python that comes in...

Conducting Gestures and Light through Helical Structures

Textiles have the potential to help technology blend into our everyday environments and objects by improving aesthetics, comfort, and ergonomics. Consumer devices have started...

Solving Rating problem using Bayesian Average

Almost every single website, app or platform on the internet has some sort of rating system in place. Whenever you purchase a product or...

Using Data Echoing to speed up Neural Network Training

Over the past decade, dramatic increases in neural network training speed have made it possible to apply deep learning techniques to many important problems....

Intelligent Locomotion via Deep Reinforcement Learning

Recent advancements in deep reinforcement learning (deep RL) has enabled legged robots to learn many agile skills through automated environment interactions. In the past...

Analysing Yeast using Machine Learning

Humans have a long history with yeast, tied to the beginnings of plant domestication — baker’s (or brewer’s) yeast, Saccharomyces cerevisiae, has been used to make...

Exploring Pre-training for Computer Vision

Exploring Pre-training for Computer Vision A common refrain for computer vision researchers is that modern deep neural networks are always hungry for more labeled data...

Evaluating Natural Language Generation using BLEURT

In the last few years, research in natural language generation (NLG) has made tremendous progress, with models now able to translate text, summarize articles, engage in conversation,...

SmartReply for YouTube Creators

SmartReply for YouTube Creators It has been more than 4 years since SmartReply was launched, and since then, it has expanded to more users with the Gmail launch and Android...

Object Detection with Neural Architecture Search

Object Detection with Neural Architecture Search Convolutional neural networks created for image tasks typically encode an input image into a sequence of intermediate features that capture...

Connecting Natural Language Instructions to Mobile UI Actions

Connecting Natural Language Instructions to Mobile UI Actions Mobile devices offer a myriad of functionalities that can assist in everyday activities. However, many of these...

Exploring Bayesian Group Testing

Exploring Faster Screening with Fewer Tests via Bayesian Group Testing How does one find a needle in a haystack? At the turn of World War...

Python vs. Java: Uses, Performance, Learning

Python vs. Java: Uses, Performance, Learning In the world of computer science, there are many programming languages, and no single language is superior to another....

Using Self-Supervision for Improving Speech Representations

There are many tasks within speech processing that are easier to solve by having large amounts of data. For example automatic speech recognition (ASR) translates spoken...

Detecting Objects through Temporal Context

Ecological monitoring helps researchers to understand the dynamics of global ecosystems, quantify biodiversity, and measure the effects of climate change and human activity, including...