SRI Blog

-By Md Zahangir Alom , Tarek M. Taha , Chris Yakopcic , Stefan Westberg, Paheding Sidike, Mst Shamima Nasrin , Brian C Van Essen , Abdul A S. Awwal, and Vijayan K. Asari Paper covers vast information on Deep learning, its History, techniques, and analysis. I would present a miniature version of it. For detailed info refer  Paper Link Since the 1950s, a small subset of Artificial Intelligence (AI), often called Machine Learning (ML), has revolutionized several fields in the last few decades. Neural Networks(NN) is a subfield of ML, and it was this subfield that spawned Deep Learning (DL). Since its inception, DL has been creating ever larger disruptions, showing outstanding success in almost every application domain. Fig. 1 shows, the taxonomy of AI. DL (using either deep architecture of learning or hierarchical learning approaches) is a class of ML developed largely from 2006 onward. Learning is a procedure consisting of estimating the model parameters so that the l

-By Yuying Ge1, Ruimao Zhang , Lingyun Wu2, Xiaogang Wang , Xiaoou Tang1, and Ping Luo The Chinese University of Hong Kong 2SenseTime Research Even as fashion image analysis gets more traction from today’s image recognition researchers, understanding fashion images remains challenging for real-world applications due to large deformations, occlusions, and discrepancies in clothing across domains and between consumer and commercial images. DeepFashion is a large-scale clothes database introduced last year by a research team from the Chinese University of Hong Kong (CUHK).  The dataset contains over 800k diverse fashion images, each labeled with 50 categories, 1,000 descriptive attributes, bounding boxes and clothing landmarks. DeepFashion was a solid foundation, but it left a number of areas for improvement. It was limited to a single clothing-item per image, sparse landmarks (4~8 only), and had no per-pixel masks. CUHK researchers recently teamed up with Chinese A

- By  Andy Coenen, Emily Reif, Ann Yuan Been Kim,  Adam Pearce, Fernanda Viégas, Martin Wattenberg  Google Research Cambridge, MA Paper Link Abstract Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic features. A natural question is how such networks represent this information internally. This paper describes qualitative and quantitative investigations of one particularly effective model, BERT. At a high level, linguistic features seem to be represented in separate semantic and syntactic subspaces. We find evidence of a fine-grained geometric representation of word senses. We also present empirical descriptions of syntactic representations in both attention matrices and individual word embeddings, as well as a mathematical argument to explain the geometry of these representations.

-By Théo Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason Mancuso, Daniel Rueckert, Jonathan Passerat-Palmbach Paper Link Secure Multiparty Computation (SMPC) is becoming increasingly popular as a way to perform operations in an untrusted environment without disclosing data. In the case of machine learning models, SMPC would protect the model weights while allowing multiple worker nodes to take part in the training phase with their own datasets, a process known as Federated Learning (FL). However, it has been shown that securely trained models are still vulnerable to reverse-engineering attacks that can extract sensitive information about the datasets directly from the model. Another set of methods, labelled as Differentially Private (DP) methods, address this and can efficiently protect the data. Abstract A new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introd