Researchers from Stanford University have introduced a new deep-learning framework for tabular data called PLATO, leveraging a knowledge graph (KG) for auxiliary domain information. It regulates a multilayer perceptron (MLP) by inferring weight vectors based on KG node similarity, addressing the challenge of high-dimensional features and limited samples. PLATO outperforms 13 baselines by up to…

Microsoft’s new Medprompt technique boosts GPT-4 to edge out Google’s Gemini Ultra on MMLU benchmark tests by a narrow margin. The technique involves dynamic few-shot learning, self-generated chain of thought prompting, and choice shuffle ensembling, proving older AI models can surpass expectations when prompted cleverly. The approach offers exciting possibilities but may require additional processing…

The article discusses the use of exponential moving average in time series analysis and its application in approximating parameter changes over time. It explores the motivation behind the method, its formula and mathematical interpretation, and introduces bias correction to overcome initial approximation challenges. The technique’s wide application scope and relevance in gradient descent algorithms are…

Researchers from Tencent AI Lab and The Chinese University of Hong Kong have introduced architectural guidelines for large-kernel CNNs. UniRepLKNet, a ConvNet model following these guidelines, excels in image recognition, time-series forecasting, audio recognition, and learning 3D patterns in point cloud data. The study also introduces the Dilated Reparam Block for enhancing large-kernel conv layers.

Apple researchers have developed DeepPCR, an innovative algorithm to speed up neural network training and inference. It reduces computational complexity from O(L) to O(log2 L), achieving significant speed gains, particularly for high values of L. DeepPCR has been successfully applied to multi-layer perceptrons and ResNets, demonstrating substantial speedups without sacrificing result quality.

Summary: The article discusses the tension between data scientists’ desire for large volumes of data and the need for data privacy and security. It emphasizes the importance of finding a middle ground in data retention and usage, while also highlighting the complexities of managing data in organizations and the impact of data security regulations.

DeepMind researchers unveiled “FunSearch,” using Large Language Models to generate new mathematical and computer science solutions. FunSearch combines a pre-trained LLM to create code-based solutions, verified by an automated evaluator, refining them iteratively. It has successfully provided novel insights into key mathematical problems and demonstrated potential in broad scientific applications, marking a transformative development in…