Category: AI/ML Research

Deep neural networks have enabled technological wonders ranging from voice recognition to machine transition to protein engineering, but their design and application is nonetheless notoriously unprincipled. The development of tools and methods to guide this process is one of the grand challenges of deep learning theory. In Reverse Engineering the Neural Tangent Kernel, we propose …

Read more “Reverse engineering the NTK: towards first-principles architecture design”

In cooperative multi-agent reinforcement learning (MARL), due to its on-policy nature, policy gradient (PG) methods are typically believed to be less sample efficient than value decomposition (VD) methods, which are off-policy. However, some recent empirical studies demonstrate that with proper input representation and hyper-parameter tuning, multi-agent PG can achieve surprisingly strong performance compared to off-policy …

Read more “Why do Policy Gradient Methods work so well in Cooperative MARL? Evidence from Policy Representation”

FIGS (Fast Interpretable Greedy-tree Sums): A method for building interpretable models by simultaneously growing an ensemble of decision trees in competition with one another. Recent machine-learning advances have led to increasingly complex predictive models, often at the cost of interpretability. We often need interpretability, particularly in high-stakes applications such as in clinical decision-making; interpretable models …

Read more “FIGS: Attaining XGBoost-level performance with the interpretability and speed of CART”

We recently published the Berkeley Crossword Solver (BCS), the current state of the art for solving American-style crossword puzzles. The BCS combines neural question answering and probabilistic inference to achieve near-perfect performance on most American-style crossword puzzles, like the one shown below: Figure 1: Example American-style crossword puzzle An earlier version of the BCS, in …

Read more “The Berkeley Crossword Solver”

Figure 1: In real-world applications, we think there exist a human-machine loop where humans and machines are mutually augmenting each other. We call it Artificial Augmented Intelligence. How do we build and evaluate an AI system for real-world applications? In most AI research, the evaluation of AI methods involves a training-validation-testing process. The experiments usually …

Read more “Rethinking Human-in-the-Loop for Artificial Augmented Intelligence”

By John P. Desmond, AI Trends Editor  The AI stack defined by Carnegie Mellon University is fundamental to the approach being taken by the US Army for its AI development platform efforts, according to Isaac Faber, Chief Data Scientist at the US Army AI Integration Center, speaking at the AI World Government event held in-person and virtually …

Read more “Best Practices for Building the AI Development Platform in Government “

By John P. Desmond, AI Trends Editor   Advancing trustworthy AI and machine learning to mitigate agency risk is a priority for the US Department of Energy (DOE), and identifying best practices for implementing AI at scale is a priority for the US General Services Administration (GSA).   That’s what attendees learned in two sessions at the AI …

Read more “Advance Trustworthy AI and ML, and Identify Best Practices for Scaling AI “

By AI Trends Staff   While AI in hiring is now widely used for writing job descriptions, screening candidates, and automating interviews, it poses a risk of wide discrimination if not implemented carefully.  Keith Sonderling, Commissioner, US Equal Opportunity Commission That was the message from Keith Sonderling, Commissioner with the US Equal Opportunity Commision, speaking at the AI …

Read more “Promise and Perils of Using AI for Hiring: Guard Against Data Bias “

By John P. Desmond, AI Trends Editor   More companies are successfully exploiting predictive maintenance systems that combine AI and IoT sensors to collect data that anticipates breakdowns and recommends preventive action before break or machines fail, in a demonstration of an AI use case with proven value.   This growth is reflected in optimistic market forecasts. …

Read more “Predictive Maintenance Proving Out as Successful AI Use Case “

By Lance Eliot, the AI Trends Insider   We already expect that humans to exhibit flashes of brilliance. It might not happen all the time, but the act itself is welcomed and not altogether disturbing when it occurs.    What about when Artificial Intelligence (AI) seems to display an act of novelty? Any such instance is bound to get our attention; …

Read more “Novelty In The Game Of Go Provides Bright Insights For AI And Autonomous Vehicles “