In artificial intelligence learning, everyone will more or less pay attention to some official accounts , but as the amount of information increases every day , the fragmented content makes everyone overwhelmed. How to mine valuable content and how to quickly access the content you need is a headache.
Therefore, Dabai will gather together the essence of the artificial intelligence field, dozens of official accounts released every week . At the same time, the classification of the system is carried out, so that everyone can understand the weekly technical trends of the artificial intelligence industry at a glance. I hope it will be helpful to everyone. If you want to view the previous weekly articles, click the link to view it. At the same time, Dabai will also extract more systematic knowledge points for each project in all weekly reports, sort them into "Summary of Dabai AI Weekly Essence" , click to view . In addition, Dabai is also constantly collecting and updating the video sharing of the authors and working experience of each project algorithm, hoping to improve the efficiency of some explorations , click to view . Finishing summary: Jiang Dabai Content cycle: 2020.09.14-2020.09.21 Synchronous public number: Jiang Dabai
table of Contents
1 Organize the list of public accounts involved
(1) I love computer vision
(2) Cver
(3) Datawhale
(4) AI algorithm and image processing
(5
) Opencv Academy (6) PaperWeekly
(7) Xinzhiyuan (8) Jishi
Platform
(9) Machine Heart
(10) Machine Learning Algorithm Engineer
(11) AI Research Institute
(12) GiantPandaCV
(13) AI Deep Learning Sight
(14) July Online Lab
(15) Artificial Intelligence Frontier Lecture
(16) AI Technology Review
(17) Machine Learning Algorithm and Python refinement
(18) Microsoft researcher AI headline
(19) VALSE
(20) AI algorithm training camp
(21) There are three AI
(22) AlWalker
(23) Qubit
(24) AI park
(25) AI artificial intelligence beginner
(26) The Road to Computer Vision
2 Summary of industry highlights
2.1 Basic knowledge
2.1.1 Deep learning related
(1) Deep learning deconvolution is the easiest to understand
Link: https://mp.weixin.qq.com/s/gqApRPCfmwRX4a0sp7b2Rw
2.1.2 Machine learning related
(1) Summary of machine learning experience in financial risk control!
Link: https://mp.weixin.qq.com/s/bKpEIPWaBkT_DFlcGBPnnQ
(2) Deep understanding of feature engineering
Link: https://mp.weixin.qq.com/s/agC2STQzqnpGBijWBvNwsQ
2.2 Research direction
2.2.1 Target detection
(1) YOLOBile with five times faster inference speed YOLOV4: real-time detection on the mobile terminal through compression and compilation (with paper download)
Link: https://mp.weixin.qq.com/s/bjbBc0e7z_-XHWX6oBeyGw
(2) Based on Yolo- V3 research on the volume occupancy rate of oil storage tanks based on satellite images
Link: https://mp.weixin.qq.com/s/KEvfqMfZD_1l1v8RGJDI0w
(3) Related theories and applications of low-latency detection in computer vision
Link: https:// mp.weixin.qq.com/s/vSRPTeAR_fMv6BGauDJftQ
(4) Painless rise point: practical Trick
link for target detection optimization : https://mp.weixin.qq.com/s/P19MJrIZMlhYviWc_OMV9A
(5) Repulsion Loss under occlusion scene Target detection
link: https://mp.weixin.qq.com/s/xLe4xxAjYGLzt_35FFvfUg
2.2.2 Three-dimensional reconstruction
(1) Three-dimensional reconstruction, visual positioning, sensor position estimation, and detailed explanation of Didi AR real-world navigation technology.
Link: https://mp.weixin.qq.com/s/3BPnA0MTdFGcGEPb4ThvQQ
(2) Teach you how to control picture characters to move? Get it with one pen!
Link: https://mp.weixin.qq.com/s/wDlQiKVIdhoA1z5HpkB4OQ
2.2.3 Attitude estimation
(1) A summary of 40 outstanding open source projects for attitude estimation
Link: https://mp.weixin.qq.com/s/_sGogZnCuPs_6wtWmFLqRQ
2.2.4 3D imaging
(1) Tencent Youtu: Introduction to the depth algorithm of 3D structured light camera
Link: https://mp.weixin.qq.com/s/NifBGfHf4CAAPCg0qF8wvA
2.2.5 NLP
(1) Different from traditional inefficient annotation, two data enhancement methods based on natural language interpretation
Link: https://mp.weixin.qq.com/s/WHMEDkfq_jaEy6LDnJW7jQ
2.2.6 Search recommendation
(1) Wang Chenyang of Tsinghua University: Introduction to lightweight Top-K recommendation framework and related papers
Link: https://mp.weixin.qq.com/s/zHiRSpIfTqEaD4PNjiWA2w
2.3 Project application
2.3.1 Image processing
(1) Some applications of Fourier transform in engineering!
Link: https://mp.weixin.qq.com/s/qK5yx2X6glJLLi7RDNpHWA
(2) Megvii Technology | Commercial side Raw image noise reduction program
Link: https://mp.weixin.qq.com/s/MuGJhzNjulxdCdhz8t4Osw
2.4 Opencv aspect
(1) Palm detection and finger counting based on OpenCV
Link: https://mp.weixin.qq.com/s/Ezuef5pxxHRwMtY1HcAh0Q
3 Summary of research & industry & interview & competition essence
3.1 Research related
(1) The difference between machine learning, data science, artificial intelligence, deep learning and statistics!
Link: https://mp.weixin.qq.com/s/4ShzWjO-1zs7d1GY_7P0yg
(2) Do a good job of data visualization skills and principles!
Link: https://mp.weixin.qq.com/s/PULCeZj1YZDV_JgTeVe1JQ
(3) Clear the fog of computing power: talk about the upper limit of different GPU computing power
Link: https://mp.weixin.qq.com/s /p2e_VetA4bLVIPGFXFMWMQ
(4)
Links to tricks (principles and code summary) in deep neural network model training : https://mp.weixin.qq.com/s/MSWhnpUlG4nYkTUZrD_T2A
(5) How to understand the generalization ability of neural networks? The CMU team took a different approach: all the secrets are in the data.
Link: https://mp.weixin.qq.com/s/eMf1tY3wJwFhhXRxnNgomw
(6) Visualization of the deep learning training process (with github source code)
Link: https://mp.weixin. qq.com/s/PG4rXVV8gqbFwc7ZAry1dw
3.2 Industry News
(1) Damedane at Station B: The essence is to change your face, you can learn it in five minutes
Link: https://mp.weixin.qq.com/s/tN48ieFcwo7Bq0Qr-XNNhg
(2) What is it like doing scientific research in Ali?
Link: https://mp.weixin.qq.com/s/X5TtofLzlEAupeCve_7itA
3.3 Interview experience
(1) 29 common interview questions and analysis of deep learning & computer vision
Link: https://mp.weixin.qq.com/s/l6ipWBpnS5R9_Kpc9NbQ6g
3.4 Competition dynamics
(1) 5.94 million prize pool! Pedestrian re-identification, remote sensing image semantic segmentation and other events are fully launched! The 2020 National Artificial Intelligence Competition is here.
Link: https://mp.weixin.qq.com/s/GQlemrKt3FI6UQZcf7H9qA
4 Python basic content
4.1 Pytorch basic tutorial
(1) Pytorch to Msnhnet model idea sharing
link: https://mp.weixin.qq.com/s/gSffbAQf8CcOJkusjN09FA
(2) Pytorch-based dynamic convolution reproduction
link: https://mp.weixin.qq.com /s/mZUSH7_7ysISoSMfxo4Vjw
4.2 Tensorflow basic tutorial
(1) Examples to introduce TensorFlow's input pipeline
link: https://mp.weixin.qq.com/s/-HiphK8gf4aRHF26MMwIWQ
(2) 10 TensorFlow techniques that algorithm practitioners must know
Link: https://mp.weixin. qq.com/s/dRDilU4m3psBPJn8ngIZVQ
