Deep Learning

Deep learning is a class of machine learning algorithms. The algorithms use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). We develop deep learning algorithms for various application such as sentiment analysis, text classification and social network mining.

Efficient deep learning focuses on optimizing neural network models to maximize performance while minimizing computational resources, such as memory, processing power, and energy consumption. These techniques not only enable the deployment of models on resource-constrained devices like smartphones and IoT devices but also contribute to reducing the environmental impact of large-scale AI systems. Our research focuses on methods to enhance the efficiency of deep learning models through pruning, quantization, knowledge distillation, and efficient inference algorithms.