By / Li Xihan, Google Developers Expert This article is excerpted from “Simple and Brutal TensorFlow 2”, reply “Manual” to get the collection. It should have been introduced long ago, the deep reinforcement learning in TensorFlow, yes, it is finally done! This article will introduce the process of implementing the Q-learning algorithm using TensorFlow in … Read more
Written by / Li Xihan, Google Developers Expert This article is excerpted from “Simple and Rough TensorFlow 2.0” TensorBoard: Visualizing the Training Process Sometimes, you want to observe the changes of various parameters during the model training process (for example, the value of the loss function). While you can check this through command line output, … Read more
Authorized Reprint from OReillyData Author | Raul Puri et al. How to Build and Train an Image Captioning Generator Using TensorFlow The image captioning model combines advances in computer vision and machine translation in recent years, using neural networks to generate captions for real images. For a given input image, the neural image captioning model … Read more
Datawhale Insights Source: Machine Heart Editorial Team Why do tree-based machine learning methods, such as XGBoost and Random Forest, outperform deep learning on tabular data?This article provides reasons behind this phenomenon, selecting 45 open datasets and defining a new benchmark to compare tree-based models and deep models, summarizing three key points to explainthis phenomenon. Deep … Read more
On Kaggle, 90% of fields including finance, tree models (like XGBoost) outperform deep learning neural network models. Let’s analyze the reasons. 01 Tree VS NN Deep learning neural network models excel in fields such as image processing and natural language, but in tabular data, such as OHLC candlestick data, neither neural networks nor transformers outperform … Read more
Yunzhong from Aofeisi Quantum Bit | WeChat Official Account QbitAI It has been a full year since ChatGPT and GPT-4 ignited a new round of artificial intelligence revolution. In this year, numerous companies both domestically and internationally have flooded into the “beast arena” of large models, accelerating the iteration and leap of large model technology. … Read more
Highlights: This article systematically reviews the application of a deep learning method—Generative Adversarial Networks (GANs)—in the auxiliary diagnosis of Alzheimer’s Disease (AD) and the processing of neuroimaging data (image denoising, image segmentation, data augmentation, and modality conversion); This article finds that compared to other methods, GANs exhibit higher classification accuracy in AD auxiliary diagnosis tasks … Read more
1 New Intelligence Column Author: Liu Shiqiang [New Intelligence Guide] This article introduces the application of deep learning methods in the field of image translation by implementing an encoding-decoding “image translator” for image enhancement, showcasing the effectiveness of deep learning applications in image translation. In recent years, deep learning has achieved remarkable results in image … Read more
Click the “Expert Knowledge” above to follow for more AI knowledge! [Introduction] Thematic aggregation knowledge is one of the core functions of Expert Knowledge, providing users with systematic knowledge learning services in the field of AI. Thematic aggregation offers users a collection of the essence (Awesome) knowledge materials about the theme from the entire network, … Read more
[Brief Note] From July 17 to 18, 2017, the first session of the Frontier Lecture Series on Intelligent Automation, organized by the Chinese Association of Automation, was held in Beijing. To promote in-depth research on the theories, methods, technologies, and applications related to Generative Adversarial Networks (GAN), the first session invited several well-known scholars from … Read more