The official Stanford AI Lab blog | Continue reading
Discovering systematic errors with cross-modal embeddings | Continue reading
Selective classification, where models are allowed to “abstain” when they are uncertain about a prediction, is a useful approach for deploying models in settings where errors are costly. For example, in medicine, model errors can have life-or-death ramifications, but abstentions … | Continue reading
The official Stanford AI Lab blog | Continue reading
One of the most common assumptions in machine learning (ML) is that the training and test data are independently and identically distributed (i.i.d.). For example, we might collect some number of data points and then randomly split them, assigning half to the training set and hal … | Continue reading
Question Answering with Knowledge From search engines to personal assistants, we use question-answering systems every day. When we ask a question (“Where was the painter of the Mona Lisa born?”), the system needs to gather background knowledge (“The Mona Lisa was painted by Leona … | Continue reading
The official Stanford AI Lab blog | Continue reading
The official Stanford AI Lab blog | Continue reading
In mid-2020, OpenAI published the paper and commercial API for GPT-31, their latest generation of large-scale language models. Much of the discourse on GPT-3 has centered on the language model’s ability to perform complex natural language tasks, which often require extensive know … | Continue reading
Knowledge Graphs (KGs) have emerged as a compelling abstraction for organizing the world’s structured knowledge, and as a way to integrate information extracted from multiple data sources. Knowledge graphs have started to play a central role in representing the information extrac … | Continue reading
Knowledge Graphs (KGs) have emerged as a compelling abstraction for organizing the world’s structured knowledge, and as a way to integrate information extracted from multiple data sources. Knowledge graphs have started to play a central role in representing the information extrac … | Continue reading
The Benefits and Bounds of Self-Supervised Pretraining | Continue reading
How heavy is an elephant? How expensive is a wedding ring? | Continue reading
How heavy is an elephant? How expensive is a wedding ring? | Continue reading
Interaction with others is an important part of everyday life. No matter the situation – whether it be playing a game of chess, carrying a box together, or navigating lanes of traffic – we’re able to seamlessly compete against, collaborate with, and acclimate to other people. | Continue reading
The official Stanford AI Lab blog | Continue reading
Imagine that you are building the next generation machine learning model for handwriting transcription. Based on previous iterations of your product, you have identified a key challenge for this rollout: after deployment, new end users often have different and unseen handwriting … | Continue reading
AI and ML products now permeate every aspect of our digital lives–from recommendations of what to watch, to divining our search intent, to powering increasingly-present virtual assistants in consumer and enterprise settings. While quality improvements are the main focus of tradit … | Continue reading
Large datasets have been shown to facilitate robot intelligence. By collecting diverse datasets for tasks such as grasping and stacking, robots are able to learn from this data to grasp and stack challenging, novel objects they haven’t seen before. | Continue reading
The NLP community has made great progress on open-domain QA, but our systems still struggle to answer complex open-domain questions in an large collection of text. We present an efficient and explainable method for enabling multi-step reasoning in these systems. | Continue reading
This post was originally on Abigail See’s website and has been replicated here with permission. | Continue reading
We introduce the problem of real-time routing for an autonomous vehicle that can use multiple modes of transportation through other vehicles in the area. We also propose a scalable and performant planning algorithm for solving such problems. | Continue reading
In recent years, the real-world impact of machine learning (ML) has grown in leaps and bounds. In large part, this is due to the advent of deep learning models, which allow practitioners to get state-of-the-art scores on benchmark datasets without any hand-engineered features. Gi … | Continue reading
A mathematical model to analyze the effects of autonomous cars on traffic congestion | Continue reading
A mathematical model to analyze the effects of autonomous cars on traffic congestion | Continue reading
We are excited to launch the Stanford AI Lab (SAIL) Blog, where we hope to share our research, high-level discussions on AI and machine learning, and updates with the general public. SAIL has 18 faculty and 16 affiliated faculty, with hundreds of students working in diverse field … | Continue reading
The official Stanford AI Lab blog | Continue reading
Every year, more people die from hospital-acquired infections than from car accidents. This means when you are admitted to a hospital, there is a 1 in 30 chance your health will get worse than had you not gone to the hospital at all. | Continue reading