Himel Das Gupta

Durga Prasad Ganta, Himel Das Gupta, Victor S. Sheng

Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network (teacher) to a smaller network (student) that can be deployed in small devices such as mobile phones. When the network size gap between the teacher and student increases, the performance of the student network decreases. To solve this problem, an intermediate model is employed between the teacher model and the student model known as the teaching assistant model, which in turn bridges the gap between the teacher and the student. In this research, we have shown that using multiple teaching assistant models, the student model (the smaller model) can be further improved. We combined these multiple teaching assistant models using weighted ensemble learning where we have used a differential evaluation optimization algorithm to generate the weight values.

Himel Das Gupta, Victor S. Sheng

Many machine learning algorithms have been developed in recent years to enhance the performance of a model in different aspects of artificial intelligence. But the problem persists due to inadequate data and resources. Integrating knowledge in a machine learning model can help to overcome these obstacles up to a certain degree. Incorporating knowledge is a complex task though because of various forms of knowledge representation. In this paper, we will give a brief overview of these different forms of knowledge integration and their performance in certain machine learning tasks.

Abhishek Murthy, Himel Das, Md Ariful Islam

Quantization, a commonly used technique to reduce the memory footprint of a neural network for edge computing, entails reducing the precision of the floating-point representation used for the parameters of the network. The impact of such rounding-off errors on the overall performance of the neural network is estimated using testing, which is not exhaustive and thus cannot be used to guarantee the safety of the model. We present a framework based on Satisfiability Modulo Theory (SMT) solvers to quantify the robustness of neural networks to parameter perturbation. To this end, we introduce notions of local and global robustness that capture the deviation in the confidence of class assignments due to parameter quantization. The robustness notions are then cast as instances of SMT problems and solved automatically using solvers, such as dReal. We demonstrate our framework on two simple Multi-Layer Perceptrons (MLP) that perform binary classification on a two-dimensional input. In addition to quantifying the robustness, we also show that Rectified Linear Unit activation results in higher robustness than linear activations for our MLPs.