Viewing profile — subho406

The model was trained on video classification, image qa and image captioning. Video captioning and video qa is not trained, yet the model shows results on those tasks.

As an author of this paper, I feel such neural networks are indeed a small step towards what we call AGI. By learning shared representations across a variety of tasks makes an AI s…

That's a really interesting idea! Giving such neural networks access to more and more modalities helps in useful transfer of information across the various nodes of the network, ma…

Full source code available at: http://github.com/subho406

Thank you for the review! We will surely correct these mistakes before submitting for final publication. The memory requirements of DNC is quite high. We used GTX 1060 for training…

I'm sorry for the misunderstanding. The reason we added the sentence because the model used in the competition was also based on DNC. But, changes were made when writing the paper,…

The demo code used for test results in the paper are available in https://github.com/cognibit/Text-Normalization-Demo . The model implementation is located in src/lib/seq2seq.py. W…

The model specifications used for the Kaggle competition was a lot different than the one mentioned in the paper. The paper compares on the same test set used by https://arxiv.org/…

Hi, we tried using a single model for the entire seq-to-seq task but the number of examples in PLAIN is huge which causes the model to perform worse on other classes. The reason we…

Hi, My name is Subhojeet and I'm a student at VIT University. I have loved computers since I was 11 and have done numerous projects. I have created games using Unity Engine and des…