Large models based on the Transformer architecture are playing an increasingly important role in artificial intelligence, especially in the fields of natural language processing (NLP) and computer vision (CV). Model compression methods reduce their memory and computational costs, which is a necessary step for implementing Transformer models on practical devices. Given the unique architecture of … Read more
Click the card below to follow「AI Vision Engine」public account ( Note when adding: direction + school/company + nickname/name ) Event-based cameras (EBCs) are a biologically inspired alternative to traditional cameras, emerging due to their advantages in energy efficiency, temporal resolution, and high dynamic range. However, developing corresponding image analysis methods is quite challenging due to … Read more
AliMei Guide Learn about Transformer, and come write one with the author. As an engineering student, when learning about Transformer, it always feels like understanding is not solid enough unless I write one myself. Knowledge gained from books is often superficial; true understanding requires practice, so take time to debug a few times! Note: No … Read more
Object detection is a fundamental task in computer vision that requires us to locate and classify objects. The groundbreaking R-CNN family[1]-[3] and ATSS[4], RetinaNet[5], FCOS[6], PAA[7], and a series of variants[8][10] have made significant breakthroughs in the object detection task. One-to-many label assignment is the core solution, which assigns each ground truth box as a … Read more
Selected from liuliu.me Author: liuliu Translated by Machine Heart Machine Heart Editorial Team Stable Diffusion may soon become popular on mobile devices. Is it difficult to run Stable Diffusion on an iPhone? The author of this article provides the answer: it’s not difficult, and the iPhone still has 50% of its performance available. As we … Read more
Author: Jeremy Jordan Translation by Machine Heart Contributors: Huang Xiaotian, Xu Di Every machine learning researcher faces the challenge of hyperparameter tuning, and during this tuning process, the adjustment of the learning rate is a crucial part. The learning rate represents the speed at which information accumulates over time in a neural network. Ideally, we … Read more
Machine Learning A magnificent history of artificial intelligence development The victory of AlphaGo, the success of autonomous driving, and breakthroughs in pattern recognition have repeatedly stimulated our nerves with the rapid development of artificial intelligence. As the core of artificial intelligence, machine learning has also attracted much attention in this rapid advancement, shining brightly. Today, … Read more
Since Tomas Mikolov from Google proposed Word2Vec in “Efficient Estimation of Word Representation in Vector Space”, it has become a fundamental component of deep learning in natural language processing. The basic idea of Word2Vec is to represent each word in natural language as a short vector with a unified meaning and dimension. As for what … Read more
Summary of Word2vec Reference Materials Let me briefly describe my deep dive into Word2vec: I first looked at Mikolov’s two original papers on Word2vec, but found myself still confused after reading them. The main reason is that these papers omit too much theoretical background and derivation details. I then revisited Bengio’s 2003 JMLR paper and … Read more
Excerpt from Sebastian Ruder Blog Author: Sebastian Ruder Translated by: Machine Heart Contributors: Terrence L This article is Part 3 of the Word Embedding Series, introducing the popular word embedding model Global Vectors (GloVe). To read Part 2, click on Technical | Word Embedding Series Part 2: Comparing Several Methods of Approximate Softmax in Language … Read more