Penn Engineering Events

CIS

  1. Events
  2. CIS

Events Search and Views Navigation

Event Views Navigation

Today

ASSET Seminar: Scallop: A Language for Neuro-Symbolic Programming, Mayur Naik (University of Pennsylvania)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT: Neurosymbolic learning is an emerging paradigm which, at its core, combines the otherwise complementary worlds of classical algorithms and deep learning; in doing so, it ushers in more accurate, interpretable, and domain-aware solutions for today’s most complex machine learning challenges.  I will begin by reviewing the various fundamentals, such as algorithmic supervision, symbolic reasoning, […]

CIS Seminar: ” Exploring the role of scientific machine learning in electric power system decarbonization”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Electric power systems lie at the heart of efforts to mitigate and adapt to the effects of climate change.  Mitigation requires shifting electricity generation away from carbon-emitting technologies toward zero carbon sources such as wind and solar generation, and converting energy end uses like transportation and space conditioning to use that electricity.  Adaptation requires designing […]

ASSET Seminar: ML for Causal Inference, Konrad Kording, University of Pennsylvania

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT Machine learning traditionally does not get at causality and causality research traditionally treats machine learning as a dangerous set of highly biased estimators. In my talk I will talk about our lab’s efforts to use machine learning as a component of more traditional quasi-experimental techniques. I will also discuss meta-learning approaches to causal inference, […]

ASSET Seminar: Domain Adaptation Under Causally Structured Distribution Shifts, Zachary Lipton (Carnegie Mellon University)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

Presentation Abstract: Faced with unlabeled data in deployment that is sampled from a different distribution than that which generated the training data, all bets are off. Moreover, while numerous heuristics have been proposed for this vague setting, it remains unclear when any among them are applicable. One way to render these problems identifiable is to […]

ASSET Seminar: What makes learning to control easy or hard?, Nikolai Matni (University of Pennsylvania)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

Presentation Abstract: Designing autonomous systems that are simultaneously high-performing, adaptive, and provably safe remains an open problem.  In this talk, we will argue that in order to meet this goal, new theoretical and algorithmic tools are needed that blend the stability, robustness, and safety guarantees of robust control with the flexibility, adaptability, and performance of […]

ASSET Seminar: The marriage of logic and learning: will it be a happily ever after?, Jyotirmoy Deshmukh (University of Southern California)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

Presentation Abstract: Huge strides have made in the widespread adoption of autonomous and human-in-the-loop cyber-physical systems (CPS), partly fueled by dramatic improvements in learning-based techniques. An important aspect of such CPS applications is that they are safety-critical: any undesirable behavior by such systems can cause serious harm to human lives or property. The formal methods […]

CIS Seminar: “Proofs, Cryptography and Quantum Information”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Many cryptographic protocols will be rendered insecure if sufficiently powerful quantum computers are built. While this remains at least a few decades away, there is another, more immediate, problem: many widely-used security analysis techniques rely on properties of classical information that do not hold in the quantum setting, rendering the security of many schemes unclear […]

ASSET Seminar: Using Large Language Models to Build Explainable Classifiers, Chris Callison-Burch (University of Pennsylvania)

Levine 307 3330 Walnut Street, Philadelphia, PA, United States

ABSTRACT: I'll present research on using large language models (LLMs) to build explainable classifiers.   I will show off work from my PhD students and collaborators on several recent research directions: Image classification with explainable features  (https://arxiv.org/abs/2211.11158) Text classification with explainable features (work in progress) The importance of faithfulness in explanations (https://arxiv.org/abs/2209.11326) (Time permitting) A […]

CIS Seminar: “Software Security Challenges in the Era of Modern Hardware”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Today’s hardware cannot keep secrets. Indeed, the past two decades have seen the discovery of a slew of attacks where an adversary exploits hardware features to leak software’s sensitive data. These attacks have shaken the foundations of computer security and caused a major disruption in the software industry. Fortunately, there has been a saving grace, namely the widespread adoption […]

CIS Seminar: “Rethinking System Design for Expressive Cryptography”

Wu and Chen Auditorium (Room 101), Levine Hall 3330 Walnut Street, Philadelphia, PA, United States

Expressive cryptography, including Secure Multi-Party Computation (SMPC) and Fully Homomorphic Encryption (FHE), has the potential to enable transformative new applications, drawing significant interest from industry. Unfortunately, it is often slow and resource-intensive, making those applications difficult to realize. For example, SMPC enables multiple organizations (e.g., hospitals) to run joint computations on their data (e.g., for […]