After centuries of intense whaling, recovering whale populations still have a hard time adapting to warming oceans and struggle to compete everyday with the the industrial fishing industry for food.
So in order to aid whale conservation efforts, scientists use photo surveillance systems to monitor ocean activity. They basically use the shape of whale’s tails and unique marking found in the footage to basically identify what species of whale they are analyzing and minutely log whale pod dynamics and movements.
For the past 40 years, most of this work has been done manually by individual scientist, leaving a huge heap of data untapped and underutilized. So in this project the main task is to basically build an algorithm to identify individual whales in the images. We will be basically analyzing HappyWhale’database of around 25k images.
The Flower classification with CNN project aims to classify flowers into 5 classes(rose, sunflower, dandelion, daisy and tuplis) using Convolutional Neural Networks. The project is deployed using Gradio platform which provides an Interface for the project where the user can upload a flower image and get the class of the flower along with the probability percentage.
In this NLP project, we are going to build a chatbot using deep learning techniques. The chatbot will be trained on the dataset which contains categories (intents), pattern and responses. We use Neural Networks to classify which category the user’s message belongs to and then we will give a random response from the list of responses. We will build a web app for chatbot using flask.
Sound Classification is one of the most widely used applications in Audio Deep Learning. It involves learning to classify sounds and to predict the category of that sound. This type of problem can be applied to many practical scenarios e.g. classifying music clips to identify the genre of the music, or classifying short utterances by a set of speakers to identify the speaker based on the voice.
So in this project we will use the audio dataset and perform some transformation which will then, suit the computer vision applications. This project basically is to notify that CNN are not just for images application.
In this tutorial, we will build a spam detection model. The spam detection model will classify emails as spam or not spam. This will be used to filter unwanted and unsolicited emails. We will build this model using BERT and Tensorflow. BERT will be used to generate sentence encoding for all emails. Finally, we will use Tensorflow to build the neural networks. Tensorflow will create the input and output layers of our machine learning model.
In this assignment, we will build a deep neural network that functions as part of an end to end machine translation pipeline. The completed pipeline will accept English text as input and return the french translation.
Virus mnist is a multiclass classification project where we have used virus mnist dataset. It has 10 classes of computer virus. CNN has been used to solve the problem and you will also go through the research paper of virus mnist detection using link provided in the project.
In this project, we will forecast furniture sales using time series techniques learnt in our assignments like sarimax, AR model etc.
In this project, you will implement GANs application on Anime dataset. You will generate fake hand writings using DCGAN and also generate fake anime images using styleGAN pretrained model.