Mohammadreza Iman

Mohammadreza Iman, John A. Miller, Khaled Rasheed et al.

Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffer from either catastrophic forgetting dilemma (losing the previously obtained knowledge) or overly biased pre-trained models (harder to adapt to target data) in finetuning pre-trained models or freezing a part of the pre-trained model, respectively. Progressive learning, a sub-category of DTL, reduces the effect of the overly biased model in the case of freezing earlier layers by adding a new layer to the end of a frozen pre-trained model. Even though it has been successful in many cases, it cannot yet handle distant source and target data. We propose a new continual/progressive learning approach for deep transfer learning to tackle these limitations. To avoid both catastrophic forgetting and overly biased-model problems, we expand the pre-trained model by expanding pre-trained layers (adding new nodes to each layer) in the model instead of only adding new layers. Hence the method is named EXPANSE. Our experimental results confirm that we can tackle distant source and target data using this technique. At the same time, the final model is still valid on the source data, achieving a promising deep continual learning approach. Moreover, we offer a new way of training deep learning models inspired by the human education system. We termed this two-step training: learning basics first, then adding complexities and uncertainties. The evaluation implies that the two-step training extracts more meaningful features and a finer basin on the error surface since it can achieve better accuracy in comparison to regular training. EXPANSE (model expansion and two-step training) is a systematic continual learning approach applicable to different problems and DL models.

Mohammadreza Iman, Khaled Rasheed, Hamid R. Arabnia

Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two major constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning, known as Deep Transfer Learning (DTL), attempts to reduce such dependency and costs by reusing an obtained knowledge from a source data/task in training on a target data/task. Most applied DTL techniques are network/model-based approaches. These methods reduce the dependency of deep learning models on extensive training data and drastically decrease training costs. As a result, researchers detected Covid-19 infection on chest X-Rays with high accuracy at the beginning of the pandemic with minimal data using DTL techniques. Also, the training cost reduction makes DTL viable on edge devices with limited resources. Like any new advancement, DTL methods have their own limitations, and a successful transfer depends on some adjustments for different scenarios. In this paper, we review the definition and taxonomy of deep transfer learning and well-known methods. Then we investigate the DTL approaches by reviewing recent applied DTL techniques in the past five years. Further, we review some experimental analyses of DTLs to learn the best practice for applying DTL in different scenarios. Moreover, the limitations of DTLs (catastrophic forgetting dilemma and overly biased pre-trained models) are discussed, along with possible solutions and research trends.

Mohammadreza Iman, Amy Giuntini, Hamid Reza Arabnia et al.

People with Parkinson's disease must be regularly monitored by their physician to observe how the disease is progressing and potentially adjust treatment plans to mitigate the symptoms. Monitoring the progression of the disease through a voice recording captured by the patient at their own home can make the process faster and less stressful. Using a dataset of voice recordings of 42 people with early-stage Parkinson's disease over a time span of 6 months, we applied multiple machine learning techniques to find a correlation between the voice recording and the patient's motor UPDRS score. We approached this problem using a multitude of both regression and classification techniques. Much of this paper is dedicated to mapping the voice data to motor UPDRS scores using regression techniques in order to obtain a more precise value for unknown instances. Through this comparative study of variant machine learning methods, we realized some old machine learning methods like trees outperform cutting edge deep learning models on numerous tabular datasets.