Benan Akça

Sometimes validation loss < training loss. Ever wondered why? 1/5

🤗

@ailabsltd Çok güzel bir düşünce tebrikler 👏

#deepfakes for cats. Cats can’t trust what’s real anymore. twitter.com/miaaselaa/stat…

Nothing like coming home on a cold Wintry day to a roomful of GPUs training deep NN models.

Applications open now! We've kicked off the Kaggle Open Data Research Grant to support academic researchers on Kaggle! 19 grants of $2k-$5k each. Application deadline: Jan 9th, 2020 ow.ly/4rLM50xyMel

@tunguz @nvidia @rapidsai @kaggle Congrats 😊

I am excited to announce that today I have joined @Nvidia. I will be part of the @Rapidsai team and help promote and develop Rapids framework for tabular data by, among other ways, competing on @Kaggle and other #ML challenges. developer.nvidia.com/rapids #AI #DS #GPU

I would be very happy if anyone interested makes comments for improvement.🙂 #kaggle #CNN #DeepLearning #ComputerVision @deeplearningtr @deeplearningai_ @DeepLearningHub kaggle.com/benanakca/kann…

I recently published a kernel in Kaggle, which includes a brief theoretical knowledge and practical application of Convolutional Neural Networks (CNN). #kaggle #CNN #DeepLearning #ComputerVision @deeplearningtr @deeplearningai_ @DeepLearningHub

NeurIPS can't handle what I just submitted to #kaggle kaggle.com/c/Kannada-MNIST

People are biased. Data is biased, in part because people are biased. Algorithms trained on biased data are biased. But learning algorithms themselves are not biased. Bias in data can be fixed. Bias in people is harder to fix. #click=https://t.co/lkLEpfDwF9" target="_blank" rel="nofollow noopener">nytimes.com/2019/12/06/bus…