siddhantray's Projects
Implementing a functional ACME client and supporting servers. Code for the Network Security Course Project, ETH Zurich, HS 2021.
Re-implementation of my Python ACME client and supporting servers in Rust.
Just a place to practice some algorithmic implementations
This is an ANN model template which uses a tanh activation function on an existing make_moons dataset. The number of hidden layers can be increased to improve prediction precision and accuracy.
This a basic ANN template which works on a sigmoid activation function. Initially the weights are created with a randomized function on a truncated normal distribution. The model further uses training and updation of weights using back propagation algorithm
News classification neural network model to classify a hierarchical news dataset. Algorithm to detect class overlap and similarities.
An attempt to clean up a deterministic noise corrupted voice audio clipping using a combination of digital filtering techniques.
BERT score for text generation
Implementation of LeNet, AlexNet and ResNet on a Fashion_MNIST Dataset.
Maximising throughput in cross traffic flows in a L2/L3 network. Contains code and poster for AdvNet at ETH Zurich, HS 2020.
CV, Resume and LaTex files for Siddhant Ray
Fixing a vulnerable web-server after intrusion. Patches for the Network Security Course Project, ETH Zurich, HS 2021.
Dotfiles ;)
An online voting app to facilitate a simple, secure and convenient voting platform for online elections.
Super-Node design code with integration of an FRR control plane with a P4 programmable data plane.
Low-Latency Data Center Network Transport
Investigating inductive biases in CNNs vs Transformers. Code and report for the Deep Learning Course Project, ETH Zurich, HS 2021.
โก Building applications with LLMs through composability โก
CI enabled compiling and version tracking for your LaTeX files.
Design of a multi-label classification model for meat policy datasets.
A hacker's userspace TCP/IP stack
An LSTM implementation carried out on a passenger number dataset for an airline company. The model has been implemented in Keras.
Hidden Markov Model (HMM) learning on the networkโs telemetry data, which is used to learn network parameters and select the best eNodeB for cell association, with the objective of ultimate ultra low latency.
This repository provides the basic python frameworks to deploy introductory level Machine Learning algorithms on Python. The main library used in the models is Sci-kit Learn.
A National Scale architecture for preemptive diagnosis and medical planning.
Packaged NS-3 application for packet data generation using message size distributions.
Code for Code for ACL 2022 paper: "MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes".
Network Traffic Transformer to learn network dynamics from packet traces. Learn fundamental dynamics with pre-training and fine-tune to multiple applications.
Countdowns to top Networking and Measurement conference deadlines.