psyyduck

joined 10 months ago
sorted by: new top controversial old
Bill Gates told a German newspaper that GPT5 wouldn't be much better than GPT4: "there are reasons to believe that we have reached a plateau" [N] in c/machinelearning@academy.garden
[–] psyyduck@alien.top 1 points 9 months ago (2 children)

Let's ask GPT4!

You're probably talking about the "fallacy of composition". This logical fallacy occurs when it's assumed that what is true for individual parts will also be true for the whole group or system. It's a mistaken belief that specific attributes of individual components must necessarily be reflected in the larger structure or collection they are part of.

Here are some clearly flawed examples illustrating the fallacy of composition.

  • Building Strength: Believing that if a single brick can hold a certain amount of weight, a wall made of these bricks can hold the same amount of weight per brick. This ignores the structural integrity and distribution of weight in a wall.
  • Athletic Team: Assuming that a sports team will be unbeatable because it has a few star athletes. This ignores the importance of teamwork, strategy, and the fact that the performance of a team is not just the sum of its individual players' skills.

These examples highlight the danger of oversimplifying complex systems or groups by extrapolating from individual components. They show that the interactions and dynamics within a system play a crucial role in determining the overall outcome, and these interactions can't be understood by just looking at individual parts in isolation.

1
[R] ConvNets Match Vision Transformers at Scale (alien.top)
 

PAPER: https://arxiv.org/abs/2310.16764

SUMMARY

The paper "ConvNets Match Vision Transformers at Scale" from Google DeepMind aims to debunk the prevalent notion that Vision Transformers (ViTs) are inherently superior to ConvNets for large-scale image classification. Using the NFNet model family as a representative ConvNet architecture, the authors pre-train various models on the extensive JFT-4B dataset under different compute budgets, ranging from 0.4k to 110k TPU-v4 core hours. Through this empirical analysis, they observe a log-log scaling law between held-out loss and compute budget. Importantly, when these NFNets are fine-tuned on ImageNet, they match the performance metrics of ViTs trained under comparable computational constraints. Their most resource-intensive model even achieves a Top-1 ImageNet accuracy of 90.4%.

The crux of the paper's argument is that the supposed performance gap between ConvNets and ViTs largely vanishes under a fair comparison, which accounts for compute and data scale. In other words, the efficacy of a machine learning model in large-scale image classification is more dependent on the available data and computational resources than on the choice between ConvNet and Vision Transformer architectures. This challenges the community's leaning towards ViTs and emphasizes the importance of equitable benchmarking when evaluating different neural network architectures.