ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Megvii Inc (a.k.a Face++) introduced ShuffleNet, which they claim to be an extremely computation efficient CNN architecture, designed for mobile devices with computing power of 10-150 MFLOPs. The ShuffleNet utilizes pointwise group convolution and channel shuffle to reduce computation cost while maintaining accuracy. It manages to obtain lower top-1 error than the MobileNet system on […]

Continue reading


A $30 AR Headset?

Much like Google Cardboard enabled cheap and easy access to VR applications, an augmented reality (AR) kit called HoloKit is now providing low-cost access to the world of AR. HoloKit made its debut this June at the Augmented World Expo USA, the world’s largest AR and VR conference and vendor exhibition. When paired with AR […]

Continue reading


CVPR2017 Honorable Mention Paper – Annotating Object Instances with a Polygon-RNN

Deep Learning dominates Computer Vision. We are all in this trend. Since AlexNet suddenly swept the competition by at least 10 percent than all other competitors in ILSVRC2012, Deep Learning never stops its pace outperforming in Image- and Video-related tasks. With years of developments, current algorithms are fairly advanced: various delicate models, fancy learning paradigms, […]

Continue reading


Deep Learning in Real Time – Inference Acceleration and Continuous Training

Introduction Deep learning is revolutionizing many areas of computer vision and natural language processing (NLP), infusing into increasingly more consumer and industrial products intelligence capabilities with the potential to impact the everyday experience of people and the standard processes of industry practices. On a high level, deep learning, similar to any automated system based on […]

Continue reading


Accelerating Convolutional Neural Networks on Raspberry Pi

Koustubh Sinhal was a co-founder and CTO of iLenze, a computer vision and visual commerce company based in India. Now, he is the CTO of AIMonk. In this blog, Koustubh tried to apply various methods to speed up the CNN and reduce their memory computational requirements. This method, with considerable computation time and controllable model […]

Continue reading


IJCAI 2017: Tencent X Synced Young Scholar Tech Night and Reception in Melbourne

International Joint Conference on Artificial Intelligence (IJCAI) 2017 will be held in Melbourne, Australia from August 19 to August 25, summoning top researchers from around the world. During this year’s conference, Synced will co-host with a tech night reception for members from Tencent’s core team and scholars to share insights on the burgeoning technology of […]

Continue reading


History and Frontier of the Neural Machine Translation

Machine translation (MT) is utilizing the power of machines to do “automatic translation of text from one natural language (the source language) to another (the target language)” [1]. The idea of doing translation using machines was first raised by Warren Weaver in 1949. For a long time (1950s~1980s), machine translation was done through the study […]

Continue reading


Customer Lifetime Value Prediction Using Embeddings

Introduction This paper was presented during the RE·WORK · Deep Learning in Retail & Advertising Summit (London). It describes the Customer Life Time Value (CLTV) prediction system deployed by ASOS.com, an online clothing shopping website. For e-commerce companies, being able to better predict the CLTV delivers a huge benefit for the business. This paper provides […]

Continue reading


30 Years of Devotion to Natural Language Processing Based on Concepts

Recently jiqizhixin.com interviewed Mr. Qiang Dong, chief scientist of Beijing YuZhi Language Understanding Technology Co. Ltd. Dong gave a detailed presentation of their NLP technology and demoed their YuZhi NLU platform. With HowNet, a well-known common-sense knowledge base as its basic resources, YuZhi NLU Platform conducts its unique semantic analysis based on concepts rather than […]

Continue reading


Andrew Ng Unveils Deeplearning.ai – New DL Courses on Coursera

Andrew Ng, one of the top minds in deep learning, loves teaching. And so, the Stanford University professor decided to re-energize the study of AI with the August 8 launch of Deeplearning.ai, a specialized deep learning educational project he has been developing since he left Chinese search engine giant Baidu in March. Deeplearning.ai is a […]

Continue reading