Background Recent studies have showed the ability of Quantum Computers to produce atypical patterns which are hard to produce classically, which gives them a distinct advantage in the domain of machine learning. However, most devices today are considered Noisy Intermediate Scale Quantum (NISQ) devices, which are limited in the circuit breadth and suffer...

AI systems are increasingly being used in critical applications where safety and reliability are paramount such as health care, autonomous driving, and financial services. Numerous AI systems operate as “black boxes,” meaning a system that processes inputs and produces outputs without revealing how it reaches its conclusions. This makes...

Background In recent years, advancements in machine learning have revolutionized various domains, but concerns about bias and unfairness in automated decision-making systems have gained significant attention. One of the causes of unfairness in AI systems is the reliance on training data. Aleatoric uncertainty refers to the inherent randomness or variability...

In the realm of natural language processing, large language models (LLMs) have emerged as powerful tools capable of understanding and generating human-like text. In terms of accuracy, LLMs are known to have performance issues, specifically when reasoning tasks are involved. And despite their advancements, LLMs often face challenges when tasked with...

The architecture information of a Deep Neural Network (DNN) model is considered a valuable, sensitive piece of property for a company. Knowledge of a DNN’s exact architecture allows any adversary to build a substitute model and use this substitute model to launch devastating adversarial attacks. Side-channel based DNN architecture stealing can...

Background Robotic prostheses have the potential to change the lives of millions of lower-limb amputees by providing critical support during legged locomotion. Powered protheses specifically enable complex capabilities including level-ground walking, running, or stair climbing, while also enabling reductions in metabolic cost and improvements in ergonomic...

The ability to predict, design, and control systems stems from our ability to reduce their dimensionality to a few key variables that accurately capture much of the behavior of the system. In theoretical physics, this has led to some of the most precise predictions ever made and the ability to control physical systems also with high precision. However,...

­One practical limitation of deep neural network (DNN) is its high degree of specialization to a single task or domain (e.g., one visual domain). This motivates the development of algorithms that can adapt DNN model to multiple domains sequentially while still performing well on past domains. This is known as multi-domain learning. Conventional...

­Recently, Deep Neural Networks (DNNs) have been deployed in many safety-critical applications. The security of DNN models can be compromised by adversarial input examples, where the adversary maliciously crafts and adds input noise to fool a DNN model. The perturbation of model parameters (e.g., weight) is another security concern, one that relates...

­Background Deep neural networks (DNNs) have been very successful in large-scale recognition tasks, but they exhibit large computation and memory requirements. To address the memory bottleneck of digital DNN hardware accelerators, in-memory computing (IMC) designs have been presented to perform analog DNN computations inside the memory. Recent IMC...