wpx_mastersMLM 
This blog-post is the subsequent part of my previous blog-post on developing question answering system on Facebook bAbI data-set. In my previous article, the bAbI data-set was described and we have extracted features for building the model. If you have directly landed on this blog-post then I would suggest you to read the previous blog-post. In this article, … Read more
Predict the Happiness on TripAdvisor reviews using Dense Neural Network with Keras : HackerEarth Challenge Date: December 21, 2017Author: Abhijeet Kumar7 Comments I participated in one HackerEarth Challenge, “Predict the Happiness” and hence I am coming up with this tutorial of the solution submitted by me which gives 88% accuracy on the test data. I was ranked among the … Read more
As in my previous post “Setting up Deep Learning in Windows : Installing Keras with Tensorflow-GPU”, I ran cifar-10.py, an object recognition task using shallow 3-layered convolution neural network (CNN) on CIFAR-10 image dataset. We achieved 76% accuracy. In this blog-post, we will demonstrate how to achieve 90% accuracy in object recognition task on CIFAR-10 dataset with help of … Read more
Automatic change detection in images of a region acquired at different times is one the most interesting topics of image processing. Such images are known as multi temporal images. Change detection involves the analysis of two multi temporal satellite images to find any changes that might have occurred between the two time stamps. It is … Read more
https://appliedmachinelearning.blog/2019/11/30/training-elmo-from-scratch-on-custom-data-set-for-generating-embeddings-tensorflow While word embedding like word2vec or glove vectors have been shown to capture syntactic and semantic information of words as well as have become a standard component in many state-of-the-art NLP architectures. But their context-free nature limits their ability to represent context-dependent information. Both Word2vec and Glove do not solve the problems like: For example, there will be … Read more
https://appliedmachinelearning.blog/2019/08/25/transfer-learning-using-fine-tuning-of-trained-model-food-images-classification In the previous blog-post, we demonstrated transfer learning using feature extraction technique and training a classifier further from the generated features. One of the strategy for transfer learning is to not only replace and retrain the classifier on top of the Convolution Neural Network (CNN) on the new data-set, but also fine tuning the weights … Read more
Date: April 1, 2019Author: Abhijeet Kumar14 Comments Named-entity recognition (NER) (also known as entity extraction) is a sub-task of information extraction that seeks to locate and classify named entity mentions in unstructured text into pre-defined categories such as the person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc. I recently participated in “Innoplexus Online Hiring Hackathon: Saving lives with AI” on Analytics Vidya … Read more
Much recently in October, 2018, Google released new language representation model called BERT, which stands for “Bidirectional Encoder Representations from Transformers”. According to their paper, It obtains new state-of-the-art results on wide range of natural language processing tasks like text classification, entity recognition, question and answering system etc. In December, 2017, I had participated in one … Read more
This blog-post is the subsequent part of my previous article where the fashion MNIST data-set was described. Also, we wrote data loader functions in the blog-post. In this article, we will focus on writing python implementation of fully connected neural network model using tensorflow. As discussed in the previous post, the fashion MNIST data-set consists of 10 classes … Read more
Tensorflow is a popular open-source framework for deep learning. It is based on dataflow programming. TensorFlow uses a dataflow graph to represent your computation in terms of the dependencies between individual operations. This leads to a low-level programming model in which you first define the dataflow graph, then create a TensorFlow session to run parts … Read more
