Yale News || TILOS Foundations team member Amin Karbasi and postdoctoral scholar Insu Han received a 2024 Roberts Innovation Fund Award for their research on making AI more powerful and cost effective.
AIthority || Considered the “black box” of machine learning, AI neural networks can expand the range of innovations and applications in different areas. AGOP is a unifying mathematical mechanism that establishes the core fundamentals explaining how neural networks learn from general machine learning models.
UC San Diego Today || The insights, published in the journal Science, can also be used to make other types of machine learning architectures more effective.
Science || Work by TILOS Foundations team member Mikahil Belkin and TILOS graduate students presents a unifying mathematical mechanism called Average Gradient Outer Product (AGOP) that characterizes feature learning in neural networks.
MIT Technology Review || An interview with TILOS Foundations team member Mikhail (Misha) Belkin about one of the biggest scientific puzzles of our time.
Notre Dame Observer || Professor Henrik Christensen speaks to the challenges and benefits of using automated vehicles for trips of short to moderate distance (zero to five miles), which account for a staggering 60% of all travel in the United States.
AI Magazine || Optimization is a universal quest, reflecting the basic human need todo better. Improved optimizations of energy-efficiency, safety, robustness, and other criteria in engineered systems would bring incalculable societal benefits. But, fundamental challenges of scale and complexity keep many such real-world optimization needs beyond reach. TILOS aims to overcome these challenges in three […]
National University News || Bridging mathematics and technology: National University’s mathematics department incorporates data science courses developed through TILOS into an updated Bachelor of Science degree program.
MIT News || Exploiting the symmetry within datasets, MIT researchers show, can decrease the amount of data needed for training neural networks.
Professor Belkin has been selected for contributions to modern machine learning theory and algorithms.
