Deep Learning

A calculator multiplies two thousand-digit numbers and takes the remainder without thinking about it. Ask a neural network to do the same thing and it becomes an open research question, one that Terence Tao helped set as a competition. The answer has to be exact, because a remainder that is off by one is simply wrong. This is what I submitted to the SAIR Foundation’s Modular Arithmetic Challenge, why the obvious approach cannot work, and the one idea that made the difference.

Special thanks to Sarvesh Talele for his meaningful contributions, support, and wisdom that helped shape this work. Traffic cameras record the circumstances of a great many collisions, but methods that read those recordings automatically are usually trained on annotated footage from the same camera. This work asks what can be recovered without any labelled real-world data at all, using three independent modules and only pre-trained weights.

The mathematics of the Transformer, worked through from the 2017 paper by Vaswani and colleagues. Scaled dot-product attention, why the scaling factor is there, multi-head attention, positional encoding, and the encoder and decoder stacks, each derived rather than asserted, for a reader who wants to understand the architecture rather than only use it.

Text2Video-Zero, from Picsart AI Research, turns a text-to-image diffusion model into a zero-shot video generator with no video training data at all. This write-up explains the method, the motion dynamics and cross-frame attention that keep a generated sequence coherent, and reports what the model produced when run, including where the results break down.

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. The core aim of this project is to take raw data, analyse it, and perform exploratory data analysis to clearly understand the underlying patterns. Using these insights, we build and train a Neural Network model to achieve accurate results. Finally, the complete system is deployed as a web application.

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. Deep learning’s breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results.

Special thanks to Archit Konde for his meaningful contributions, support, and wisdom that helped shape this work. The purpose of this study is to familiarise the reader with the foundations of neural networks. Artificial Neural Networks (ANNs) are algorithm-based systems that are modelled after Biological Neural Networks (BNNs).

Special thanks to Mega Satish for her meaningful contributions, support, and wisdom that helped shape this work. This paper aims to demonstrate the efficiency of the Adversarial Open Domain Adaption framework for sketch-to-photo synthesis. The unsupervised open domain adaption for generating realistic photos from a hand-drawn sketch is challenging as there is no such sketch of that class for training data.

Special thanks to Mega Satish and Hasan Rizvi for their meaningful contributions, support, and wisdom that helped shape this work. In the present study, we propose to implement a new framework for estimating generative models via an adversarial process to extend an existing GAN framework and develop a white-box controllable image cartoonization, which can generate high-quality cartooned images/videos from real-world photos and videos.