Podcast #128: We chat with Kent C Dodds about why he loves React and discuss what life was like in the dark days before Git. Listen now.

New answers tagged

0

I think you may have a class imbalance problem here, if I am reading your output correctly. You have 20,000 negative examples, but only 8000 positive ones, and you are minimizing binary cross entropy without re-weighting the examples, so your model can achieve a low-ish loss just by consistently outputing a value close to 0. This forms a local optima in the ...


2

Another explanation of deep learning as an end-to-end framework is in deep learning, pre-processing or feature extraction steps are not necessary. So it only uses a single processing step, which is to train the deep learning model. In other traditional machine learning methods, some separated feature extraction steps usually required. For example in image ...


1

This is relevant when you have two or more neural networks serving as components to a larger architecture. Training this architecture in an end-to-end manner means simultaneously training all components (i.e. training it as a single network). The best example I can think of are image captioning architectures. These usually comprise of two networks: a CNN ...


1

Yes you can, a few years ago I made a simple CNN for a single Arabic phoneme classification. You can use spectogram or using MFCC / MFSC as features, as long all data has the same size (use padding or cropping if needed). You may need RNN if you want to combine some phonemes to recognize a single word or longer.


0

We can manipulate a model's test data set if the machine learning model takes user input and uses it to resample test data set. The actual training dataset of the ML model does not get manipulated, but if we figure out the ML model through an exploratory attack (sending a lot of inquiries to the ML model to find out its nature), we can generate a training ...


0

In adverserial machine learning, someone (program or human) attempts to fool an existing model with a malicious input. The best human example would be an optical illusion. The human brain's model for image processing starts outputting wrong information when looking at an optical illusion. So in the end we see wrong colour, shape, etc. In this case, the ...


1

They don't have acces to the original training or test dataset. Machine learning environments are build on the premise of a benign environment. The models are trained on real data (real inputs). When someone sends a made up input (fake input) it is very easy to fool the model. This is used for example in image recognition. Imagine a fotograph of a panda. ...


1

I don't think he said that at all. Going back to the talk you'll see he mentions mode collapse comes from the naivete of using alternating gradient-based optimization steps because then $min_{\phi}max_{\theta}L(G_\phi, D_\theta)$ starts to look a lot like $max_{\theta}min_{\phi}L(G_\phi, D_\theta)$. This is problematic because in the latter case the ...


1

Read on Fully Convolutional Networks (FCN). There is a lot of papers on the subject, first was "Fully Convolutional Networks for Semantic Segmentation" by Long. The idea is quite close to what you describe - preserve spatial locality in the layers. In FCN there is no fully connected layer. Instead there is average pooling on top of last low-resolution/high-...


3

I have had similar thoughts about neural networks before. Convolution layers are layers of two dimensional nodes effectively passing the spacial data so why don't we use two dimensional hidden layers to receive information out of them. I'm sure someone has used this type of implementation before. I believe the papers bellow are using this. Part of the ...


2

Your dataset class probably have a lot of preprocessing code. You should use a dataloader. It will prefetch data from the dataset when the GPU is processing. Also, you can process all the data beforehand and save to a file. Multiple GPU cannot scale as the GPU have to get all data to one GPU to calculate the loss. The performance of 4 GPU is around 3.5x. A ...


0

In theory, deeper architectures can encode more information than shallower ones because they can perform more transformations of the input which results in better results at the output. The training is slower because back propagation is quite expensive, as you increase the depth, you increase the number of parameters and gradients that need to be computed. ...


0

For recreating an image exactly the same as the original, you can use an autoencoder. This basically use AI Layers to encode the image raw pixel values to a vector of floats, drastically decreasing the representing vector. Afterwards another AI Layer increases the dimensions back to the original image. The method does not required labels, as it only refer to ...


Top 50 recent answers are included