My Time at NUS, Singapore

Singapore is home to some of the best schools in the field of Computer Science, specifically . The going on there is unparalleled. Colleges like Nanyang Technological University (NTU) and have a great reputation all over the world for their CS programs. Artificial Intelligence cutting edge research National University of Singapore (NUS) An opportunity presented itself to me when I was in my college in SRMIST, Chennai, India. A Global Academic Internship Programme ( ) by Corporate Gurukul, which sends students interested/experienced in to study under world class faculty. I wasn't letting this pass, so I signed up for it, cleared the interview and got in! GAIP Artificial Neural Networks and Big Data to NUS It was December 2018 and I was on my flight to Singapore 🇸🇬. The was very exciting because of it's thorough covering the basics and advanced topics related to Artificial Neural Networks(ANN) and Big Data (more on these topics later). trying to implement whatever that was taught in the lectures keeping in mind the business value of the project that was being developed. Academic Internship syllabus In a span of 15 days we had to work on two projects We covered ANN for the first 8 days, followed by Big Data in the remaining. ANN Lectures were delivered by and . Dr. Lek Hsiang Hui , Dr. Tan Wee Kek Dr. Wang Wei Firstly, we had . It was a really good insight and added value to my understanding of the same concept. Dr. Lek Hsiang Hui who gave us an introduction to Data Analytics Explained the different types of and gave a few examples of how the data flows between different states, is modified and then a decision is taken based on the output. Decision Models also was covered with a great flow digram describing each of various stages involved like . Data mining Data Extraction, Data Cleaning, Data Aggregation, Data Representation, Data Interpretation Basics of and implementing various mathematical formulae was also taught, which included . R programming Measures of Location, Measures of Shape, Measures of Dispersion and Measures of Association Secondly, we had in a very intuitive manner, and I was able to grasp most of the concepts with ease. Things I understood and implemented: Dr. Tan Wee Kek who presented the concepts of Machine Learning Simple and Multi and it's problems Linear Regression Python Data Science Libraries like Numpy, Scipy, Matplotlib and Scikit Learn and it's types: Decision Trees, Bayesian Classifier, Logistic Regression, SVM (Support Vector Machines) Classification : K-Means, K-Mediods, Hierarchical Methods Clustering using Classification, Association and Clustering Text Mining and KDD An artificial neural network is designed to function like the neurons in the brain. Lastly, . These topics were harder to understand with the level of Calculus involved but Dr. Wei did a great job at teaching us the basics. Here's everything that I learned and implemented: Dr. Wang Wei introduced us to topics revolving around Artificial Neural Networks : Problems with Logistic Regression Why ANN and (GD) Algorithm Back Propagation Gradient Descent Some advanced GD Algorithms like , , and Stochastic GD Minibatch GD RMSProp Adam Training Techniques: Random Initialisation, ReLU, Dropout : Pooling, Padding, Strides and some common CNN Architectures Convolutional Neural Networks : Vanilla RNN and LSTM Recurrent Neural Networks We had to present our Artificial Neural Networks Course Project two days after our final lecture. Those days went by really quickly with little or no sleep as me and my group mates hustled to finish our project called Quick Draw. We wanted to make something that has great scope for real-world implementation and helps the society. . Our program tracks the strokes of the user and gives an output predicting what the user is trying to draw in real-time of various labeled hand drawn images in the Numpy Array format. We downloaded the data of 4 classes (20,000 images each) and started training it with different algorithms. First we started off with SVM, then K-Means Clustering, then Feed-Forward Neural Network, then Convolutional Neural Network and finally Long Short-term Memory (LSTM). . So we decided to use those two models and we made a front end for our project using OpenCV library which is basically taking input of our strokes from the keyboard. Quick Draw uses the existing Google's Dataset We found out that CNN and LSTM gave us the highest accuracies You can checkout the project here . Now moving on to the . This course was delivered by , or as we call him, . He helped us work on some really complicated linux commands, broke them down for us so that we find it easy. Here are the topics that I learned and implemented: Big Data Course, the second one of our internship Ravindra Kumar God of Linux What is and how it is changing the world Big Data Problems in Big Data and it's features, Hadoop vs RDBMS Hadoop The : HDFS, Yarn, MapReduce, HBase, ZooKeeper, Pig and Hive Hadoop Ecosystem : NameNode, DataNode, SSH-ing into these nodes without a password Setting up Node Cluster using Ambari Management , Commissioning and De-commissioning, Resource Manager, Scheduler Setting up HDFS using Shell Commands Basic Queries and Data Ingestion mechanisms using HIVE Sqoop Programming Mapreduce After the lectures, we had to work on a in which we set up a deployed on a platform and managed using . We had to do everything from scratch, set up between the three nodes, setup , creating a local repository, transferring data from the local repository to and then performing operations on that Data. We chose the book called 'Sherlock' from the Gutenberg Library and . Every step of the project was done mostly through shell commands which was really cool and helped us understand the working of Linux commands, when and where to use them. project three node cluster Ambari password-less SSH Java, JDBC, Hadoop environments on the .bashrc file HBASE performed Word-Count and MapReduce programs on it It was a to learn from the best in the world and work on projects under their guidance. I also would like to , they were always there to help us out with any difficulty that we would face and help us overcome it. really enriching experience thank the Teaching Assistants(TA) for the course Puru Sharma and Devvrit Khattri Thank you for reading!