Welcome to shuffleai.blog!

AI Tech blogs about NLP, computer vision and self-driving cars powered by deep learning.

Blog4 mask rcnn inference
Nov 14, 2021 Understanding Mask R-CNN Basic Architecture

Basic architecture of Mask R-CNN network and the ideas behind it. ResNet backbone, RPN, RoIAlign, object detection brand, mask generation branch.

Blog10
Dec 14, 2021 Gap Sentences Generation in PEGASUS

In this article, we discussed three selection strategies of Gap Sentence Generation for pre-training and their effects in downstream tasks. Ind-Orig, which is one of the principle selection strategies, has best performances compared with other 5 variants of GSG.

blog7
Dec 9, 2021 Deploy a Deep Learning Model to a REST API

This article will go through how to deploy deep learning model to a REST API with Sagemaker, Lambda and API Gateway.

blog8
Dec 1, 2021 How to Create New Roles in AWS IAM

In this article, we go through 2 cases of creating IAM roles. The first one is used for SageMaker and can read, write to S3 bucket in SageMaker. The second one is used for Lambda use case.

Blog6 geometric path tracking
Nov 16, 2021 Three Methods of Vehicle Lateral Control: Pure Pursuit, Stanley and MPC

In this article, we will discuss three methods of vehicle lateral control: Pure pursuit, Stanley, and MPC. I will also go through codes to achieve a self-driving car following a race track.

Blog5 three reference points of the kinematic model
Nov 14, 2021 Simple Understanding of Kinematic Bicycle Model

2D bicycle model can be expressed as a simplified car model. This is a classic model that does very well at capturing vehicle motion in normal driving conditions.

Blog1 bricks
Nov 11, 2021 Quickly learn and use Git for your project

In this tutorial, we learned how to update our own work from the local machine to the remote repository. Meanwhile, we also learned how to track other people’s work and downloads or pull to our local working space. So we can work together as a team.

Blog3 road sign
Sep 9, 2021 How to Improve Performance of Deep Learning models

Learn about how to find main problems of the deep learning model such as overfit and underfit. So we can get the most promising ways to improve the deep learning model.

Blog2 lego bricks
Aug 27, 2021 PyTorch coding: a binary classification example

Learn about how to solve a simple binary classification problem with neural network model implemented in PyTorch.

Blog1 bricks
Sep 27, 2021 NLP Concepts Part 1

Learn about NLP concepts: word embedding, language model, BLEU and ROUGE metric.

Blog4 mask rcnn inference
Nov 14, 2021 Understanding Mask R-CNN Basic Architecture

Basic architecture of Mask R-CNN network and the ideas behind it. ResNet backbone, RPN, RoIAlign, object detection brand, mask generation branch.

Blog3 road sign
Sep 9, 2021 How to Improve Performance of Deep Learning models

Learn about how to find main problems of the deep learning model such as overfit and underfit. So we can get the most promising ways to improve the deep learning model.

Blog2 lego bricks
Aug 27, 2021 PyTorch coding: a binary classification example

Learn about how to solve a simple binary classification problem with neural network model implemented in PyTorch.

Blog1 bricks
Sep 27, 2021 NLP Concepts Part 1

Learn about NLP concepts: word embedding, language model, BLEU and ROUGE metric.

Blog10
Dec 14, 2021 Gap Sentences Generation in PEGASUS

In this article, we discussed three selection strategies of Gap Sentence Generation for pre-training and their effects in downstream tasks. Ind-Orig, which is one of the principle selection strategies, has best performances compared with other 5 variants of GSG.

Blog6 geometric path tracking
Nov 16, 2021 Three Methods of Vehicle Lateral Control: Pure Pursuit, Stanley and MPC

In this article, we will discuss three methods of vehicle lateral control: Pure pursuit, Stanley, and MPC. I will also go through codes to achieve a self-driving car following a race track.

Blog5 three reference points of the kinematic model
Nov 14, 2021 Simple Understanding of Kinematic Bicycle Model

2D bicycle model can be expressed as a simplified car model. This is a classic model that does very well at capturing vehicle motion in normal driving conditions.

Blog7
Dec 9, 2021 Deploy a Deep Learning Model to a REST API

This article will go through how to deploy deep learning model to a REST API with Sagemaker, Lambda and API Gateway.

Blog8
Dec 1, 2021 How to Create New Roles in AWS IAM

In this article, we go through 2 cases of creating IAM roles. The first one is used for SageMaker and can read, write to S3 bucket in SageMaker. The second one is used for Lambda use case.

Blog9
Nov 11, 2021 Quickly learn and use Git for your project

In this tutorial, we learned how to update our own work from the local machine to the remote repository. Meanwhile, we also learned how to track other people’s work and downloads or pull to our local working space. So we can work together as a team.

About us

Welcome to SHUFFLE Blogs!

We provide AI tech blogs about computer vision, natural language processing and self-driving cars. Our authors and developers are two enthusiasts of AI. They are glad to share their learning and application experiences with you. Thank you for your visit!

Yan Ding

Yan does research in machine learning, deep learning, and self-driving cars. She likes exploring NLP, computer vision problems based on deep learning. She is enthusiast in AI. She also has experience in deploying and scaling deep learning models on Cloud(AWS, GCP).

Xiang Zhang

Xiang Zhang is a deep learning engineer. He has some experiences in applying machine learning/deep learning algorithms to computer vision, NLP, and reinforcement learning problems. He will continously contribute to our blog.

Get in touch

We are happy to hear from you. You can leave us a messeage here if you have any questions. Or you can contact us directly via our LinkedIn.

person_pin
email
message