With the continuous development of network technology and the ever-expanding scale of e-commerce, the number and variety of goods grow rapidly and users need to spend a lot of time to find the goods they want to buy. To solve this problem, the recommendation system came into being. The recommendation system is a subset of the Information Filtering System, which can be used in a range of areas such as movies, music, e-commerce, and Feed stream recommendations. The recommendation system discovers the user's personalized needs and interests by analyzing and mining user behaviors and recommends information or products that may be of interest to the user. Unlike search engines, recommendation systems do not require users to accurately describe their needs but model their historical behavior to proactively provide information that meets user interests and needs.
To meet the growing interest in Deep Reinforcement Learning (DRL), we sought to construct a DRL-driven Atari Pong agent and accompanying visualization tool. Existing approaches do not support the flexibility required to create an interactive exhibit with easily-configurable physics and a human-controlled player. Therefore, we constructed a new Pong game environment, discovered and addressed a number of unique data deficiencies that arise when applying DRL to a new environment, architected and tuned a policy gradient based DRL model, developed a real-time network visualization, and combined these elements into an interactive display to help build intuition and awareness of the mechanics of DRL inference.
In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to the input images are sufficient to fool the most powerful neural networks. Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle, PyTorch, Caffe2, MxNet, Keras, TensorFlow and it can benchmark the robustness of machine learning models. Compared to previous work, our platform supports black box attacks on Machine-Learning-as-a-service, as well as more attack scenarios, such as Face Recognition Attack, Stealth T -shirt, and DeepFake Face Detect.
Microsoft, Google, Facebook, and Amazon have all done it -- and now Baidu's doing it, too. The Chinese tech giant has open sourced one of its key machine learning tools, PaddlePaddle, offering the software up to the global community of AI researchers. This move has become common among tech firms as they pour more and more resources into their AI work. Open sourcing your tools is a good way to attract talent, but it also allows companies to shape the development of a field that's becoming increasingly central to consumer tech, underpinning everything from voice interfaces to auto-sorting photo galleries. Baidu's big claim for PaddlePaddle is that it's easier to use than rival programs.
Baidu has released the toolkit for its quantum machine learning platform, Paddle Quantum, which it says will enable developers to build and train quantum neural network models. Built on the Chinese tech giant's deep learning platform PaddlePaddle, the toolkit also includes quantum computing applications. Paddle Quantum, currently available on GitHub, comprises a set of quantum machine learning toolkits, including a quantum chemistry library and optimisation tools, as well as three quantum applications: quantum machine learning, quantum chemical simulation, and quantum combinatorial optimisation. Several underlying functions of PaddlePaddle, including matrix multiplications, also enable Paddle Quantum to support quantum circuit models and general quantum computing research, Baidu said in a statement on Wednesday. Asian country has began investing in quantum technology and is at a similar starting point with other economic powers in this field, says Shanghai-born Turing Award winner Andrew Yao.