Deep Learning

tl;dr A step-by-step tutorial to train a state-of-the-art model with flair and BERT for named entity recognition (NER) in mandarin, 中文命名实体识别, on a Weibo dataset. Our model beats the state-of-the-art by 20+ percentage points. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

tl;dr A step-by-step tutorial to train a state-of-the-art model for sentiment analysis on mandarin food delivery reviews using the XLNet architecture. We will use Google Colab’s free Jupyter Notebook in the cloud. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

tl;dr A step-by-step tutorial to train a state-of-the-art model for named entity recognition (NER), the task of identifying persons, organizations and locations from a piece of text. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

tl;dr A step-by-step tutorial to train a sentiment analysis model to classify polarity of IMDB movie reviews with XLNet using a free Jupyter Notebook in the cloud. The IMDB Movie Reviews Dataset and XLNet The Internet Movie Database (IMDb) movie reviews dataset is a very well-established benchmark (since 2011) for sentiment analysis performance. It’s probably the first large-ish (50,000 train+test), balanced sentiment analysis dataset, making it a very nice dataset for benchmarking on....

tl;dr A step-by-step tutorial to train a state-of-the-art model to detect sarcasm 🙄 from tweets with a free Jupyter Notebook in the cloud. Sooo Impressive Sarcasm Detection Model on Tweets Recently Venture Beat published (and Communications of the ACM referenced) a news article titled “AI researchers made a sarcasm detection model and it’s sooo impressive” which detailed how researchers from China had come up with a “sarcasm detection AI” that “achieved state-of-the-art performance on a dataset drawn from Twitter”....

tl;dr Google Colab and Paperspace Gradient both provide Jupyter notebooks with free GPUs in the cloud to code, train and test your ML models. Which is the better option? In this article we compare them. Our final answer is to use both depending on your current ML workloads and requirements. What is Google Colab and what is Paperspace Gradient? If we had to pick one particular tool that makes ML easier for everyone, it would be cloud Jupyter notebooks....

tl;dr We feature 10 of the top Computer Vision (CV) code repositories from Singapore. These include popular implementations of YOLO3, EfficientDet, DeepLab, FaceBoxes and other models ranging from activity recognition to eye tracking. The ranking is decided based on the total Github stars of the repositories. 10. Dual Path Networks Architecture of DPNs. Retrieved from Github. This repository contains the code and trained models of Dual Path Networks which won the 1st place in Object Localization Task in ILSVRC 2017, and was a Top 3 team with on all competition tasks (Team: NUS-Qihoo_DPNs)....

tl;dr We feature 10 of the top Natural Language Processing (NLP) code repositories on Github from Singapore. The ranking is decided based on the total stars (stargazer count) of the repositories. 10. A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction Architecture of the multilayer convolutional model with seven encoder and seven decoder layers. Retrieved from the official paper. Code and model files for the paper: “A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction” (Published at AAAI-18)....

tl;dr We feature 5 of the top machine learning code repositories on Github from Singapore. The Top 5 is made up of popular implementations of state-of-the-art Computer Vision (CV) and Natural Language Processing (NLP) models and even a high-frequency trading project. The ranking is decided based on the total stars (stargazer count) of the repositories. 5. PyTorch Implementation of EfficientDet Architecture of EfficientDet including a weighted bi-directional feature pyramid network (BiFPN)....

tl;dr NeurIPS is the largest and argubably the most prestigious machine learning research conference internationally. We look at the 44 accepted publications from singapore-based authors in this 2020 edition of the conference, which is happening live this week (6 - 12 Dec 2020). What is NeurIPS? NeurIPS is the Conference and Workshop on Neural Information Processing Systems (abbreviated as NeurIPS and formerly NIPS). It is the largest conference in Artificial Intelligence with a specific focus on machine learning and neuroscience....