Hello, my name is Samyak Jain. I am currently working as a Data and Solutions Analyst at smrtr. I Completed my Bachelor of Advanced Computing (Hons) degree at Australian National University, and I major in Intelligent Systems. I have worked on a variety of data projects, which include data analysis, visualization, and implementing machine learning pipelines. I will showcase some of my projects here, and link them to their GitHub repositories.
Having gained some valuable experience working as a data and solutions analyst at smrtr which invloved all the aspects from data mining to the ultimate product, I am now ready for new oppounities and take a step forward in my career . Some of my relevant Work Experience in the field is listed below.
Jan 2021 - Present
Liaising with various stakeholders internally and externally, handling large quantities of data from multiple sources, working on multiple tasks & projects simultaneously and dealing with any queries. Data mining, wrangling and intepreting quality of data in/out. Developing strategies to optimise the quality of statistical results. Maintaining databases. Solely Responsible for handling tableau architecture and providing insights through visualization
July 2019 - May 2020
Employed various machine learning models to build a predictive modeling approach to better inform industry experts about using Magnesium alloys with ideal mechanical properties to make lightweight vehicles. Main idea was to use Artficial Intelligence to predict alloy compositions that could be useful for future metallic alloys which in turn helps to reduce the weight of the vehicles.
July 2018 - Nov 2018
Built a small and simple game called Frogger which is an adaptation of the game played in PC. Duties included heavy involvement in developing the User Interface and back end code.
July 2018 - Jan 2021
• Foundations of Computing • Data Wrangling • Data Mining • Information Theory • Strategic Thinking: Game theory • Intro to Machine Learning • Document Analysis • Advance Computing Research Methods • Software Design Methodologies • Intro To Data and Security • Advanced Computing Project • Neural Networks: Deep Learning • Statistical Machine Learning • Computer Vision
June 2016 - May 2018
Data Structures • Software Design using Object Oriented Programming • Java Programming • Computer Organisation and Assembly Language Programming • Combinational and Sequential Logic • Formal Languages and Automata Theory • Design and Analysis of Algorithms • Computer Architecture
Below are just some of my projects that i have done in my spare time or in uni work or so. These include Data analysis, Visualization , machine learning pipelines as well as projects related to computer vision.
A combination of lightweight, high specific strength, and good castability make magnesium alloys a promising engineering material for the automotive and aerospace industries. Vehicle weight reduction is one of the major means available to improve automotive fuel efficiency. High-strength steels, Aluminium (Al), and polymers are already being used to reduce weight significantly, but substantial additional reductions could be achieved by greater use of low-density magnesium (Mg) and its alloys. This project herein, therefore, relies on the use of machine learning, to assist in the development of A.I. to predict alloy compositions that are potentially useful for future metallic alloys. This study shows how a machine learning approach is able to offer acceptable precision predictions with respect to the main mechanical properties of metals.
Using the Breast Cancer Wisconsin (Diagnostic) Database, we can create a classifier that can help diagnose patients and predict the likelihood of a breast cancer. A few machine learning techniques will be explored. A few known machine learning classifiers were comapared against each other to obtain the best classifier. GridSearchCV was implemented that helped us obtain the best setting paramters for the desire classifier. In this particular exercise, Support Vector Machine was able to acheive the highest average and overall accuracy.
Basic Image I/O operations performed. Equilization Task, Histogram , Histogram Equlization , R-G-B Equlization. Image Denoising , Gaussian Filter , Sobel Filter. Image rotation, Forward and backward Mapping.
The goal of this study was to experiment with the network reduction technique based on distinctiveness. We implemented the technique on a simple feed-forward neural network that dealt with the summarized version of the images and extended our implementation to deep learning that dealt with actual images . Our findings showed us that using deep learning and transfer learning to detect faces-emotion had a higher performance measure than using the summarized version .In addition to this, we experimented with the number of hidden neurons and our research showed us that overall the pruning technique was useful to an extent in removing undesirable and redundant neurons and increasing the performance of our model with a large number of hidden neurons.But on the other hand when the number of hidden neurons are small the pruning had a negative effect on the performance measure.
Implemented Harris Corner Algorithm. Non- Maximum Supression to detect only relevant corners. K-Means ALgorithm. K means ++ .
In this age of deep learning , neural nets with large number neurons and parameters are very common . But , a rule of thumb for obtaining good generalisation is to make sure that we build the smallest system that fits the data. It is essential to prune the network for making it more efficient. In this paper we discuss about one such pruning technique that we learned from a previous paper that is based on the angles between the unit vectors of the hidden layer which are similar or complementary towards the output. Initially we build a simple three layer network to classify different emotions of faces and then compare the results after applying the technique and see how it affects our neural network.
I am currently open to any job opportunites as a data analyst / data engineer. Please feel free to contact me anytime. Thank you for your taking time and going through my portfoilo and I look forward to hearing from you soon about any potential opportunity at your company.
26, Bowman Street
Macquarie, ACT
2614 Australia
samyak1901@gmail.com
u6734495@anu.edu.au
Mobile: (+61) 415 412 545
