mbeissinger

You might want to check out the conversational chunking from this paper:

On Memory Construction and Retrieval for Personalized Conversational Agents https://arxiv.org/abs/2502.05589

Our driving force is to make this technology as accessible as possible to as many people as possible. We believe that machine learning will be a huge new way that people interact with computers going forward to better their lives.

Lobe will always let you train custom machine learning for free on your computer. We hope this becomes a vibrant ecosystem, and the business model around the edges can come later for value-add services.

I don't see a way to edit the title -- is that possible for someone who isn't OP?

We also want to bundle some examples with future releases so you can have data to start, great suggestion!

We believe there are several advantages of Lobe over tools like Google AutoML :) Lobe is making the entire process of creating custom machine learning accessible, from creating your dataset to training and playing with your model, to integrating it into apps:

* Easy to use - no coding, cloud configuration or machine learning experience required.

* Free & private - train for free on your own computer without uploading your data to the cloud. No accounts required.

* Ship anywhere - available for both Mac and Windows. Export your model and ship it on any platform you choose.

AutoML requires paid accounts with high friction setup and is focused on just training a model on your data. You would have to pay and retrain your model manually every time you want to make an iteration. Lobe gives fluidity with iterating and providing feedback to your model through Play.

No catch! We are first and foremost trying to make this technology accessible to as many people as possible, and we want to grow an ecosystem around it. Business models around that can come later.

Yep we are starting with image classification for this initial beta launch, but plan to expand to more data types and problem types in future releases! The vision is to make a tool usable by anyone to build custom machine learning

I would love to see a video of that!

I believe it is this xkcd https://xkcd.com/1425/ sorry research teams :D

Hey Markus from Lobe here :) all images and labels stay private to your computer, we don't ever see any of it. We only collect some generic app usage data for telemetry if you opt-in to sharing analytics after installing Lobe.

Hi, Markus here from the Lobe team. The Lobe app is free and you will always be able to train for free on your computer! Our goal is to make machine learning accessible to anyone.

Great work as always from hardmaru :)

Thanks! Finding the right way and levels to present granularity was definitely a challenge for us developing this product.

We are currently accepting applications for private beta users, and don't have public pricing information yet.

Yeah! Adam and I met at NIPS 2015 when I demoed a gui prototype for OpenDeep, talking about ways to let non-coders build neural nets. Around the same time, we saw that QC Brain video Mike posted and we all started talking and unifying around this vision of helping people who aren't experts get started with designing and adding intelligence to apps. From there we formed the vision for Lobe and the rest is history!

Our vision is to be the tool that starts with great settings for beginners but lets you graduate into the internals as you become more expert - at the lowest level you can interactively create computation graphs and see their results as you change settings, sort of like eager mode for ml frameworks on steroids (or other visual computation graph programs that designers use like Origami/Quartz Composer).

The lobes in the UI are all essentially functions that you double click into to see the graph they use, all the way down to the theory/math.

If you want more comprehensive ways to learn the theory, I highly recommend Stanford's 231n course (http://cs231n.stanford.edu/) and the Goodfellow/Bengio/Courville Deep Learning book (https://www.amazon.com/Deep-Learning-Adaptive-Computation-Ma...)

Yep growing as a platform is the vision! We are committed to accessibility for people using models/components vs. paying but good point about considering the opportunity cost of someone going to algorithmia with a model once it is trained.

Unreal was one of the early inspirations for going the visual route - completely agree!

We are focusing on free to access any model explicitly shared by the user and pay for training/deploy resources as a service, but might consider mixing in a paid route for users to monetize their unique trained models.

We are also exploring exporting to other formats to run in different environments locally, or even code generation.

Yes definitely, we support desktop currently with the Tensorflow SavedModel download if you need the model locally, or using the REST API for an application with online connectivity.

Thanks! Acumos has a similar vision of making it easy to build, share, and deploy AI. We are also heavily focused on the iteration and feedback loop time when developing AI applications, and importantly on helping users understand what is going on with the model. That way you can know the limits of the system in production, or know how/where to improve the data and help reduce bias.

We plan to support when we get time series data and video upload implemented.

Thanks! Yeah our approach is that diverse applications need to be able to go in and customize the models to be useful, at least for the next few years until the algorithms for AutoML get better and replace the engineers :P

Web service with the option to download a compiled Tensorflow SavedModel or CoreML file if you need the model locally.

We are working with private beta users now, will have pricing up when it is public.

Thanks! One of the benefits of Lobe is that users who build models from scratch can publish and share to use in other documents, like a community model zoo. We do this for the current architectures internally, but the goal is for the community to help keep up with the firehose state-of-the-art in ML.

Something really interesting we have discussed for a future feature is being able to train a model using the data of which architectures end up working best for different data types so that Lobe can use AutoML to suggest better templates starting out, or on the fly while you are building the model.

We are working on supporting time series data, so coming soon.

Our initial thoughts for pricing model are to be based on compute and keep as low as possible - we want this to be accessible to as many people as possible and do things like enable local training with Tensorflow.js for free. For cloud API deployment, we will price around the backend compute cost on AWS/GCP for gpu instances plus some margin for us maintaining the distributed setup and scaling of serving a machine learning model.

Thanks! We used the water tank as the first end-to-end test using the product, and made a website that calls the API every minute to monitor the water level in a dashboard.

The architecture implemented using Lobes for object detection is called Yolo v2 (https://pjreddie.com/darknet/yolo/). It is fairly state-of-the-art for that type of problem and has ~70 million parameters that are being learned (matrices that get multiplied and added together). With a webcam and a GPU over the network, we typically see ~1-5 fps with a lot of network overhead sending output images - looking to make that faster for API deployment. The paper site above shows it having 62.94 Bn FLOPS