Blog Posts

Find my full blog here

Find my highlighted posts below!

• Try your first Neural Network for Neural Information Retrieval

  In this tutorial, we'll build a simple NIR system. We'll use BM25 retrieval and the Sentence Transformers library for the bi-encoder model.

• Train your first gMLP Model for classifying images

  In this tutorial, we will train a gMLP model on CIFAR-100 dataset. We will build the model using Keras and train it on Kaggle using GPU acceleration.

• Train your first MLPMixer model for classifying images

  In this tutorial, we are going to train the MLPMixer model on CIFAR-100 dataset. We will build the model using Keras and train it on Kaggle using GPU acceleration.

• Train your first Neural Network for Large Scale Text Classification

  In this tutorial, we will train a simple Dense Neural Networks for Large Scale text classification.

• Train your first KNN Model for Collaborative Filtering

  In this tutorial, we will build and train a KNN Model for item-based Collaborative Filtering to build a Movie Recommendation system.

• Train your first Super Learner Ensemble Model for classification

  In this tutorial, we will build a Super Learner ensemble and check its performance against the different models that the ensemble is made out of.

• Train your first Siamese Neural Network for detecting Face Similarity

  In this tutorial, we will implement and train a siamese neural network for detecting face similarity using one-shot learning.

• Train your first Neural Network for Named Entity Recognition

  In this tutorial, we are going to train a BiLSTM Network for NER using Annotated Corpus for Named Entity Recognition dataset provided by Kaggle.

• Train your first Convolutional Neural Network for classifying news articles

  In this tutorial, we will classify BBC news articles into their appropriate categories using 1-D convolutional neural networks layers instead of a RNN or LSTM.

• Train your first Neural Network with Attention for Abstractive Summarisation

  In this tutorial, we are going to train a Transformer model for abstractive summarization task by training it on news articles and their summaries.

• Train your first Neural Network for Image Similarity Search

  In this tutorial, we use metric learning in order to search the nearest neighbours or similar images to a given image from the CIFAR-10 dataset.

• Train your first Autoencoder for reconstructing a noisy image

  In this tutorial, we will train an Autoencoder to denoise MNIST images to reproduce clean pictures of digits from the MNIST dataset.

• Train your first CycleGAN for Image to Image Translation

  In this tutorial, we will train a CycleGAN model to translate photos of horses to zebras, and back again to horses. The model we are going to train is the very model which was trained in the CycleGAN paper. CycleGANs are great for unsupervised training capabilities.

• Build a QA System using BERT and Hugging Face

  Build a Question Answering System using a pre-trained BERT model and tokenizer using context based on first match Wikipedia article.

• Train your first Neural Network for Image Captioning using Transfer Learning

  Build and train an Encoder-Decoder style network to build an Image Captioning model using Transfer Learning from the ResNet50 model.

• Train your first Neural Machine Translation Model

  Train your first Neural Network for Machine Translation using Encoder-Decoder style LSTM to translate German phrases into English. Inspired by Google's GNMT model used in Google Translate.

• Train your first LSTM Model for Text Generation

  In this tutorial, we are going to build a neural network with LSTM layers using Keras and train it on Alice's Adventures in Wonderland by Lewis Carroll as a part of Project Gutenberg.

• Build your first Neural Network for Image Restoration

  Sneak peak into the methodology on which Nvidia's DLSS works! In this tutorial, we build an SR-CNN model that learns end-to-end mapping of low resolution to high-resolution images. As a result, we can use it to improve the image quality of low-resolution images.

• Solving LPN Problem with Machine Learning: An Introduction

  "Is it actually possible for an AI to break an encrypted message?". Take a look at the Learning Parity with Noise or LPN Problem coupled with a tutorial to help us understand how an AI can break encryption.

• Train your first Optimized Deep Learning Model

  Deep Learning models are data-hungry models and require a lot of training time and it only grows as number of layers increase. Using RMSProp Optimizer, train a CNN Model on CIFAR 10 dataset using Keras on Kaggle!

• Train your first Multimodal Learning Model

  Train your first multimodal learning model with Images and Text modalities using Keras and Kaggle Notebooks.