A survey of methods of interpretability of neural networks: from gender bias mitigation to interpreting BERT embeddings in a psycholinguistic manner.
Bio:
Department of Computer Science and Technology
A survey of methods of interpretability of neural networks: from gender bias mitigation to interpreting BERT embeddings in a psycholinguistic manner.
Bio:
Abstract not available
*ABSTRACT*: Audio, as a novel digital phenotype (e.g., the body sound), has been studied and demonstrated to be effective via the power of computer audition (CA), an emerging technology that enables the computers to listen to the real world similar to or even beyond the human ear capacity.
This presentation will explore advancements in genomic research, starting with de novo assembly, where Šikić's lab leads with novel applications of long reads technology.
Abstract not available
The emerging machine learning (ML) applications put exploding demands on hardware systems, and it is important to deliver high throughput, low latency and low energy consumption, in order to sustain the thriving development of cognitive systems and applications.
Abstract not available
We address a problem that arises at the confluence of three recent trends: the popularity of storage-coupled photovoltaic (PV) systems amongst homeowners, the rapid proliferation of electric vehicles (EVs) with potential for bidirectional energy storage within PV-enabled single-family homes, and third, the surge in remote wo
Abstract not available
*ABSTRACT*: Sensing is an effective means to connect the physical world and digital space. Exploring the intelligent sensing capability has drawn researcher’s great attention.