Day 3 (7/10/19): Experimentation with Classifiers

Today I took a step forward toward a more specific focus on machine learning and neural networks. After quickly reviewing yesterday's material through Datacamp exercises on python and Numpy, I spent most of the morning completing tutorials on implementing various classifiers using the machine learning software Scikit-learn.

First using the simple K Nearest Neighbors Classifier, I learned how to fit classifiers to data, use the classifiers to predict targets for new test data, and evaluate the accuracy and errors of each classifier using Confusion Matrices and Classification Reports. Then, I applied what I learned to both the Iris (classifying three types of flowers) and MNIST (classifying handwritten digits) datasets implementing different types of models such as Support Vector Machine (both Linear and RBF), Gaussian Process, and Multilayer Perceptron Classifiers.

In the afternoon, I watched a Youtube playlist which provided an introduction to neural networks including a basic Python implementation of Linear Regression. After finishing that simple neural network, I started learning more specifically about Convolutional Neural Networks (CNNs), especially used in computer vision problems. With guidance from resources such as Stanford's CS231 and RIT's Deep Learning for Vision courses, I hope to be able to implement CNNs in code later this week.

Comments

Day 9 (7/18/19): Incrementally Learning CUB200

Today I continued my work learning about incremental learning models by testing out different strategies on the CUB200 dataset. From what I understand from reading various articles, there seem to be five different approaches to mitigating catastrophic forgetting in lifelong learning models. These are regularization methods (adding constraints to a network's weights), ensemble methods (train multiple classifiers and combine them), rehearsal methods (mix old data with data from the current session), dual-memory methods (based off the human brain, includes a fast learner and a slow learner), and sparse-coding methods (reducing the interference with previously learned representations). All of these methods have their constraints and I don't believe it is yet clear what method (or what combination of different methods) is best. Full rehearsal obviously seems to be the most effective at making the model remember what it had previously learned but given that all training exam...

Day 30 (8/16/19): Final Presentations

Today we gave our final presentations, and everyone did a great job. I would like to thank everyone who helped me with this amazing experience! I'm very thankful to have had the opportunity to work on such interesting research with such amazing people this summer.

Day 24 (8/8/19): Multilayer Perceptron Experiment

I continued gathering more results for my presentation today, and the data table is coming along nicely. We are able to see a significant trend that using Mahalanobis instead of Baseline Thresholding recovers much of the OOD recognition that is lost with streaming or incremental models. The SLDA model appears to be a lightweight, accurate streaming model which can be paired with Mahalanobis to be useful as an embedded agent in the real world. For the purposes of demonstrating catastrophic forgetting, I ran five experiments and averaged the results for a simple incrementally trained MLP. Obviously, the model failed miserably and was achieving only about 1% of the accuracy of the offline model. Including this is only to show how other forms of streaming and incremental models are necessary to develop lifelong learning agents. A diagram of a simple multilayer perceptron.

RIT CIS Summer Internship

Search This Blog