saintarian
1. How much work is it to add bindings for new languages? 2. I know you provide conductor as a service. What are my options for workflow recovery if I don't have outbound network access? 3. Considering this came out of https://dbos-project.github.io/, do you guys have plans beyond durable workflows?
Ontology-Oriented Software Development
Beyond model training: The untapped potential of AutoML platforms
Four questions concerning the internet, part two
Object detection without bounding boxes
How to change the satellite imaging industry
Ways to use a data engine to improve your ML model
Service Oriented Design Applies to ML Too
[1] https://www.nyckel.com/semantic-image-search [2] https://www.nyckel.com/docs/text-search-quickstart
This is one of the methods mentioned in the article. I don't have implementation experience with the other string distance measures in the article (under "normalized string" in the table), except for Q-grams. Compared to the above method Q-grams don't scale as well and are not as robust because it doesn't encapsulate an understanding of the semantics of the text.
[1] github.com/facebookresearch/faiss [2] github.com/google-research/google-research/tree/master/scann [3] www.pinecone.io
Show HN: Semantic Search of Millions of NFTs
https://www.nyckel.com/nft-finder/
The sprawling world of NFTs would benefit from a semantic search app. So we made one.Try text queries like “a city in space”, “monet”, or “cat wearing a red hat”. Or image queries by uploading an image or by clicking on one of NFTs on the right.Enjoy!
Author of the blog post here. It was definitely written from my narrow viewpoint and experience. Our goal is to make more solutions accessible to software developers and instinct was the same as yours - a lot of ML can be within the realm of engineering (even small / one-person teams) and that there are accidental complexities standing in the way of wider use. Our solution (AutoML+SaaS) def doesn't work for every situation. I'm curious to hear more of your thoughts on how ML can be made more accessible to Eng (and vice versa).
I wrote this as someone who considers himself a half-decent software engineer trying to use ML for a side project and feeling frustrated by all the effort and "accidental complexity" involved. Why focus on software engineers and ML in this post/rant/company? Because "software is eating the world" and having ML be more accessible to software engineers will broaden the range of problems they can solve.
Thanks for all the comments - I acknowledge all/most of the criticisms as valid. A SaaS/AutoML solution won't work for everyone and definitely not for every problem, and it won't be the only answer to making ML more approachable.
Yes, you are right - 'includes X invocations' are per month.
We benchmarked ourselves against Google AutoML and HuggingFace, looking at both user experience and model performance, and wrote it up in a blog post that may interest you: https://www.nyckel.com/blog/automl-benchmark-nyckel-google-h...
Our goal is to be cost-competitive, even for bigger projects. Given how early we are, our pricing structure is still being worked on, especially for high-volume.
Integrating with labeling solutions is in our roadmap. In the meantime, our API should enable any data/labeling integrations.
Named entity recognition is also in the roadmap. Would love to hear more about your use-case and we can give you access to the beta when ready.
We tried to make the lingo developer-friendly. We think of models as functions that transform inputs to outputs. Instead of writing code to do so, as developers usually do, you train the function by providing desired outputs to sample inputs.
- To see all cases where the model disagrees with your annotation: Function Output = Disagrees, Desired Output = Any.
- To see the least confident predictions from the model: Function Output = Any, Desired Output = Any, Sort By = Least Confident Prediction.
Your idea us helping you pick a confidence threshold is a good one. We'll get that into our near-term roadmap.
We use a technique called cross-validation to seperate training and test data. We have that documented here: https://www.nyckel.com/docs#cross-validation
Would love to talk more about your use case so we prioritize the right things for model export. Drop me a line (george at nyckel dot com).
Thanks for the feedback on the UI! None of us are UI experts and we agree that it isn't great. We're working to make it better.
Launch HN: Nyckel (YC W22) – Train and deploy ML classifiers in minutes
Hi HN, we’re George, Oscar, and Dan, the founders of Nyckel (https://nyckel.com). Nyckel allows developers with no ML experience to train and deploy ML functions to classify images and text with very little training data. We let you go from a few labeled data points to a serverless machine-learned classifier in minutes.The ML-as-a-Service space is dense, including some recent YC companies; so...