Bottom-up Top-Down Detection Transformers For Open Vocabulary Object Detection – Machine Learning Blog | ML@CMU

We perform open vocabulary detection of the objects mentioned in the sentence using both bottom-up and top-down feedback. Object detection is the fundamental computer vision task of finding all “objects” that are present in a visual scene. However, this raises the question, what is an object? Typically, this question is side-stepped by defining a vocabulary … Read more

Automate PowerPoint Presentation Report with Python | by Cornellius Yudha Wijaya | Jan, 2023

Automate the report instead of manually adoption Photo by Nghia Nguyen on Unsplash Data people and business people are always working together hand-to-hand. One of the common activities between data people and business users is to make PowerPoint report presentations which comprise all the important messages. Sometimes it feels too much for data people to … Read more

Competitive programming with AlphaCode

Note: This blog was first published on 2 Feb 2022. Following the paper’s publication in Science on 8 Dec 2022, we’ve made minor updates to the text to reflect this. Solving novel problems and setting a new milestone in competitive programming Creating solutions to unforeseen problems is second nature in human intelligence – a result … Read more

2022-23 Takeda Fellows: Leveraging AI to positively impact human health | MIT News

The MIT-Takeda Program, a collaboration between MIT’s School of Engineering and Takeda Pharmaceuticals Company, fuels the development and application of artificial intelligence capabilities to benefit human health and drug development. Part of the Abdul Latif Jameel Clinic for Machine Learning in Health, the program coalesces disparate disciplines, merges theory and practical implementation, combines algorithm and … Read more

Keeping Learning-Based Control Safe by Regulating Distributional Shift

To regulate the distribution shift experience by learning-based controllers, we seek a mechanism for constraining the agent to regions of high data density throughout its trajectory (left). Here, we present an approach which achieves this goal by combining features of density models (middle) and Lyapunov functions (right).

In order to make use of machine learning and reinforcement learning in controlling real world systems, we must design algorithms which not only achieve good performance, but also interact with the system in a safe and reliable manner. Most prior work on safety-critical control focuses on maintaining the safety of the physical system, e.g. avoiding falling over for legged robots, or colliding into obstacles for autonomous vehicles. However, for learning-based controllers, there is another source of safety concern: because machine learning models are only optimized to output correct predictions on the training data, they are prone to outputting erroneous predictions when evaluated on out-of-distribution inputs. Thus, if an agent visits a state or takes an action that is very different from those in the training data, a learning-enabled controller may “exploit” the inaccuracies in its learned component and output actions that are suboptimal or even dangerous.

Read more