We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neural memory that uses novel physical addresses and pointer manipulation techniques to mimic human and computer symbol processing abilities. PANM facilitates pointer assignment, dereference, and arithmetic by explicitly using physical pointers to access memory content. Remarkably, it can learn to perform these operations through end-to-end training on sequence data, powering various sequential models. Our experiments demonstrate PANM's exceptional length extrapolating capabilities and improved performance in tasks that require symbol processing, such as algorithmic reasoning and Dyck language recognition. PANM helps Transformer achieve up to 100% generalization accuracy in compositional learning tasks and significantly better results in mathematical reasoning, question answering and machine translation tasks.

As banks move to responsibly integrate artificial intelligence and machine learning capabilities into their business processes, the American Bankers Association this week urged regulators to focus on providing greater clarity around the use of AI and ensuring that there is a consistent regulatory standard for its use across all financial services providers. In a letter responding to a recent request for information on AI and machine learning, ABA emphasized that given the stringent supervision and regulation banks are already subject to, "new banking regulations are not necessary or warranted to address AI." Rather, regulators should focus their efforts on clarifying existing regulations and guidance to address AI-related risks and ensure that banks can continue to innovate in a safe, responsible manner, ABA said. Among other things, ABA specifically called for additional guidance around fair lending risk in the use of AI, and how banks should be managing disparate impact risks. The association also emphasized the need for coordination across the regulatory agencies on the issuance of any AI-related guidance, and encouraged the agencies to support voluntary pilot or innovation programs that banks may choose to participate in. "AI makes banking services better, cheaper, and more widely available, and will continue to do so. While these benefits do not come without risks, we believe that the robust bank regulatory structure already captures these risks today," the association said.

As banks move to responsibly integrate artificial intelligence and machine learning capabilities into their business processes, the American Bankers …