-
### What
- We currently perform OCR, NSFW detection server-side.
- We could do some of that work on-device for high-end devices
### Why
- prevent bad images from reaching the server
- let …
-
Let's try to characterize data pollution - i.e., has this LLM been pretrained on this corpus?
Simple task: pick a random passage - chop into half. Feed first half into LLM, ask it to complete the p…
-
Hello everyone. I've modified some content on the file called kernel_neon.h , I imitate the original kernel(12x8x2) and wrote a new kernel(8x8x8), and I've run the benchmark, It seems that the results…
-
WWW
As a machine learning engineer looking for efficient solutions to out of domain detection, I would like to understand research and state of the art in this field.
- A recent paper called Is fine…
-
Run an experiment to evaluate the performance of a simulated annealing gradient descent (SA-GD) approach compared to traditional gradient descent (GD). The purpose of this experiment is to understand …
-
More a question than an issue but will there be the possibility of using the 'GPU' or Neural engine whilst in eager execution mode in the near future? I am benchmarking some software and would like to…
-
#### Goal:
Implement, train and test a LaneNet algorithm and test it with the open source datasets CULane and TuSimple
#### Assigments:
- Understand how the ML-algorithms works
- Implement the M…
-
# Description
The goal of this project is to expand our current understanding of the different **practical aspects** of recently proposed QML algorithms (i.e [[1]](https://arxiv.org/abs/1907.02085), …
ElePT updated
2 years ago
-
In your recent [paper](https://arxiv.org/abs/2103.10360), you introduce a new method, GLM (General Language Model), and refer to this algorithm by the name "GLM" in your paper.
I wanted to offer th…
-
#### Description
We want to compare gensim and [SageMaker](https://aws.amazon.com/ru/sagemaker/):
- LSI (after #1896) vs [SageMaker PCA](https://docs.aws.amazon.com/sagemaker/latest/dg/pca.html)
…