spaduf

cross-posted from: https://slrpnk.net/post/5710029

Institution: Wikiversity
Lecturer: Boud Roukema
Subject: #physics #specialrelativity #generalrelativity
Description: Special relativity and steps towards general relativity is a one-semester Wikiversity course that uses the geometrical approach to understanding special relativity and presents a few elements towards general relativity. The course may be used in a traditional university, within the conditions of the free licensing terms indicated at the bottom of this Wikiversity web page. It may be modified and redistributed according to the same conditions, for example, via the Wikiversity and Wikimedia Commons web sites.

The courses are substantially more complete than typical OCW courses and include new custom-created content as well as materials repurposed from MIT classrooms. The materials are also arranged in logical sequences and include multimedia such as video and simulations.

cross-posted from: https://slrpnk.net/post/5710029

Institution: Wikiversity
Lecturer: Boud Roukema
Subject: #physics #specialrelativity #generalrelativity
Description: Special relativity and steps towards general relativity is a one-semester Wikiversity course that uses the geometrical approach to understanding special relativity and presents a few elements towards general relativity. The course may be used in a traditional university, within the conditions of the free licensing terms indicated at the bottom of this Wikiversity web page. It may be modified and redistributed according to the same conditions, for example, via the Wikiversity and Wikimedia Commons web sites.

Institution: Wikiversity
Lecturer: Boud Roukema
Subject: #physics #specialrelativity #generalrelativity
Description: Special relativity and steps towards general relativity is a one-semester Wikiversity course that uses the geometrical approach to understanding special relativity and presents a few elements towards general relativity. The course may be used in a traditional university, within the conditions of the free licensing terms indicated at the bottom of this Wikiversity web page. It may be modified and redistributed according to the same conditions, for example, via the Wikiversity and Wikimedia Commons web sites.

Institution: Stanford
Lecturer: Fei-Fei Li, Justin Johnson, Serena Yeund
University Course Code: CS 231
Subject: #computervision #machinelearning

Description: Computer Vision has become ubiquitous in our society, with applications in search, image understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, localization and detection. Recent developments in neural network (aka “deep learning”) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This lecture collection is a deep dive into details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. From this lecture collection, students will learn to implement, train and debug their own neural networks and gain a detailed understanding of cutting-edge research in computer vision.

cross-posted from: https://slrpnk.net/post/5501378

For folks who aren't sure how to interpret this, what we're looking at here is early work establishing an upper bound on the complexity of a problem that a model can handle based on its size. Research like this is absolutely essential for determining whether these absurdly large models are actually going to achieve the results people have already ascribed to them on any sort of consistent basis. Previous work on monosemanticity and superposition are relevant here, particularly with regards to unpacking where and when these errors will occur.

I've been thinking about this a lot with regards to how poorly defined the output space they're trying to achieve is. Currently we're trying to encode one or more human languages, logical/spatial reasoning (particularly for multimodal models), a variety of writing styles, and some set of arbitrary facts (to say nothing of the nuance associated with these facts). Just by making an informal order of magnitude argument I think we can quickly determine that a lot of the supposed capabilities of these massive models have strict theoretical limitations on their correctness.

This should, however, give one hope for more specialized models. Nearly every one of the above mentioned "skills" is small enough to fit into our largest models with absolute correctness. Where things get tough is when you fail to clearly define your output space and focus training so as to maximize the encoding efficiency for a given number of parameters.

For folks who aren't sure how to interpret this, what we're looking at here is early work establishing an upper bound on the complexity of a problem that a model can handle based on its size. Research like this is absolutely essential for determining whether these absurdly large models are actually going to achieve the results people have already ascribed to them on any sort of consistent basis. Previous work on monosemanticity and superposition are relevant here, particularly with regards to unpacking where and when these errors will occur.

I've been thinking about this a lot with regards to how poorly defined the output space they're trying to achieve is. Currently we're trying to encode one or more human languages, logical/spatial reasoning (particularly for multimodal models), a variety of writing styles, and some set of arbitrary facts (to say nothing of the nuance associated with these facts). Just by making an informal order of magnitude argument I think we can quickly determine that a lot of the supposed capabilities of these massive models have strict theoretical limitations on their correctness.

This should, however, give one hope for more specialized models. Nearly every one of the above mentioned "skills" is small enough to fit into our largest models with absolute correctness. Where things get tough is when you fail to clearly define your output space and focus training so as to maximize the encoding efficiency for a given number of parameters.

cross-posted from: https://mander.xyz/post/8095934

Looks like we're getting company!