How to define neural network neuron-by-neuron?
So we want to have a random brain-like neuron mess. Meaning:
- We have AxB inputs and CxD outputs.
- We want to have K (where K >= CxD) neurons that are connected to each other at random.
- Yet so that all K neurons are connected to at least one of AxB inputs,
- And all K neurons are connected to at least one CxD output.
Something like ths (here AxB=5, K=4, CxD=2):
Operations that neurons shall do are weighted summ + some reduction like LeakyReLu.
So one can imagine that when connection randomnes is controlled so that connections are localised over image patches alike layers of CNN it can produce intresting results.
How one could do such thing (handle neurons one-by-one) in PyTorch?
There are two issues here: The major issue is how to randomly sample the connections, and a minor issue of how to optimize a sparse linear layer.
As for the minor issue, you can implement a sparse fully-connected layer based on the linked answer.
As for the random connectivity, you'll have to implement it in a way that there are no "loops"
- How can I tell when the model is overfitting?
- StratifiedKFold vs KFold in scikit-learn
- Training a Keras model to identify leap years
- Ideas for Extracting Blade Tip Coordinates from masked Wind Turbine Image
- Macro VS Micro VS Weighted VS Samples F1 Score
- Doing PyWavelets calculation on GPU
- Training loss increases instead of decrease with epochs
- How to save a Dataset in multiple shards using `tf.data.Dataset.save`
- why explain logit as 'unscaled log probabililty' in sotfmax_cross_entropy_with_logits?
- What is the loss function used in Trainer from the Transformers library of Hugging Face?
- Using features extracted using a pretrained CNN as new features for an CNN/NN
- InvalidArgumentError: No DNN in stream executor while training a TensorFlow RetinaNet model on Google Colab
- ALS (Alternating Least Square) algorithm in multiple rankings for a user
- How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?
- How to create image of confusion matrix in Python
- Cross-validation with nb method
- GPU utilization almost always 0 during training Hugging Face Transformer
- The “Forward/Backward Passage Size” is too large for the pytorch model (Yolov3)
- How many images(minimum) should be there in each classes for training YOLO?
- Why do neural networks work so well?
- Will larger batch size make computation time less in machine learning?
- Why KL divergence is negative in Pytorch?
- Creating a voice identification system using machine learning
- Forward pass with all samples
- override pytorch Dataset efficiently
- fit method in sklearn
- Calibrating Probabilities in lightgbm or XGBoost
- Implementation of F1-score, IOU and Dice Score
- Is it ok to have the training history very similar to the validation history?
- How to understand Shapley value for binary classification problem?