home.social

#convolutionalneuralnetwork — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #convolutionalneuralnetwork, aggregated by home.social.

  1. I remembered playing with DeepDream computer vision program that uses CNN (Convolutional Neural Network) almost 10 years ago. How fun it was to be able to run it locally on one my machines despite being very slow. Luckily I was able to find an already trained model, because training it locally was not feasible for me.

    #convolutionalneuralnetwork #cnns

  2. I remembered playing with DeepDream computer vision program that uses CNN (Convolutional Neural Network) almost 10 years ago. How fun it was to be able to run it locally on one my machines despite being very slow. Luckily I was able to find an already trained model, because training it locally was not feasible for me.

  3. I remembered playing with DeepDream computer vision program that uses CNN (Convolutional Neural Network) almost 10 years ago. How fun it was to be able to run it locally on one my machines despite being very slow. Luckily I was able to find an already trained model, because training it locally was not feasible for me.

    #convolutionalneuralnetwork #cnns

  4. I remembered playing with DeepDream computer vision program that uses CNN (Convolutional Neural Network) almost 10 years ago. How fun it was to be able to run it locally on one my machines despite being very slow. Luckily I was able to find an already trained model, because training it locally was not feasible for me.

    #convolutionalneuralnetwork #cnns

  5. I came across a neat paper, Deep Image Prior arxiv.org/abs/1711.10925 The idea is that the structure of a deep convolutional neural net, CNN, is a prior that allows it to be useful for image problems. In the paper they used an untrained CNN to do things like upscaling an image. I had seen CNN's being used for that kind of task before but I thought the training was what allowed them to work well. This paper is arguing that the structure is enough.
    #machinelearning
    #convolutionalneuralnetwork

  6. I came across a neat paper, Deep Image Prior arxiv.org/abs/1711.10925 The idea is that the structure of a deep convolutional neural net, CNN, is a prior that allows it to be useful for image problems. In the paper they used an untrained CNN to do things like upscaling an image. I had seen CNN's being used for that kind of task before but I thought the training was what allowed them to work well. This paper is arguing that the structure is enough.
    #machinelearning
    #convolutionalneuralnetwork

  7. I came across a neat paper, Deep Image Prior arxiv.org/abs/1711.10925 The idea is that the structure of a deep convolutional neural net, CNN, is a prior that allows it to be useful for image problems. In the paper they used an untrained CNN to do things like upscaling an image. I had seen CNN's being used for that kind of task before but I thought the training was what allowed them to work well. This paper is arguing that the structure is enough.
    #machinelearning
    #convolutionalneuralnetwork

  8. I came across a neat paper, Deep Image Prior arxiv.org/abs/1711.10925 The idea is that the structure of a deep convolutional neural net, CNN, is a prior that allows it to be useful for image problems. In the paper they used an untrained CNN to do things like upscaling an image. I had seen CNN's being used for that kind of task before but I thought the training was what allowed them to work well. This paper is arguing that the structure is enough.
    #machinelearning
    #convolutionalneuralnetwork

  9. While we're (needfully) obsessing over AI in the world of direct human affairs, there's an explosion of productive exploitation of deep learning in the natural (often anthropogenically-influenced) world.

    And these applications need to survive more than an elevator pitch.

    Side-product, perennially surfaced during weekly climate research trawl:

    sciencedirect.com/science/arti

    #DeepLearning
    #TreeMortality
    #WildFire
    #ConvolutionalNeuralNetwork

  10. While we're (needfully) obsessing over AI in the world of direct human affairs, there's an explosion of productive exploitation of deep learning in the natural (often anthropogenically-influenced) world.

    And these applications need to survive more than an elevator pitch.

    Side-product, perennially surfaced during weekly climate research trawl:

    sciencedirect.com/science/arti

    #DeepLearning
    #TreeMortality
    #WildFire
    #ConvolutionalNeuralNetwork

  11. While we're (needfully) obsessing over AI in the world of direct human affairs, there's an explosion of productive exploitation of deep learning in the natural (often anthropogenically-influenced) world.

    And these applications need to survive more than an elevator pitch.

    Side-product, perennially surfaced during weekly climate research trawl:

    sciencedirect.com/science/arti

    #DeepLearning
    #TreeMortality
    #WildFire
    #ConvolutionalNeuralNetwork

  12. While we're (needfully) obsessing over AI in the world of direct human affairs, there's an explosion of productive exploitation of deep learning in the natural (often anthropogenically-influenced) world.

    And these applications need to survive more than an elevator pitch.

    Side-product, perennially surfaced during weekly climate research trawl:

    sciencedirect.com/science/arti

    #DeepLearning
    #TreeMortality
    #WildFire
    #ConvolutionalNeuralNetwork

  13. While we're (needfully) obsessing over AI in the world of direct human affairs, there's an explosion of productive exploitation of deep learning in the natural (often anthropogenically-influenced) world.

    And these applications need to survive more than an elevator pitch.

    Side-product, perennially surfaced during weekly climate research trawl:

    sciencedirect.com/science/arti

    #DeepLearning
    #TreeMortality
    #WildFire
    #ConvolutionalNeuralNetwork

  14. phys.org/news/2023-09-ai-algor

    "…typically composed of stacks of #graphene layers with a relative twist…attracted immense attention from the #condensedmatter community…due to their high tunability and…make these systems a perfect playground for testing theories from #stronglycorrelatedphenomena…but directly obtaining these details from experimental data is often an ill-defined inverse problem…we trained a #convolutionalneuralnetwork…to recognize features of #nematicity from the data…"