Day 8 (7/17/19): Incremental Lifelong Learning

I spent the majority of today reading recent papers outlining various approaches to achieving effective incremental learning deep learning models. There seems to be a wide variety of proposed systems with no general consensus on which is best or how to evaluate the different models. In fact, incremental learning does not always mean the same thing in different papers because some models incrementally learn classes while others incrementally learn datasets or even stray from the batch setting altogether by learning from streaming data. As a result there does not yet exist a standardized way of evaluating which models are actually best at achieving lifelong learning because they are often tested on significantly different tasks.

After lunch, my advisor and I went through a presentation made by Tyler Hayes, another PhD student in the lab. It discussed many of the problems and proposed solutions which I was reading about and explained the focus of a lot of the research the kLab is doing.

Tomorrow I plan to spend the day trying to implement incremental learning into my own model to classify the CUB200 dataset. It should be challenging but also rewarding once I manage to finish it.

Comments

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.

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...

RIT CIS Summer Internship

Search This Blog