There remains a list of unanswered research questions on deep learning (DL), including the remarkable generalization power of overparametrized neural networks, the efficient optimization performance despite the non-convexity, and the mechanisms behind flat minima in generalization. In this paper, we adopt an information-theoretic perspective to explore the theoretical foundations of supervised classification using deep neural networks (DNNs). Our analysis introduces the concepts of fitting error and model risk, which, together with generalization error, constitute an upper bound on the expected risk. We demonstrate that the generalization errors are bounded by the complexity, influenced by both the smoothness of distribution and the sample size. Consequently, task complexity serves as a reliable indicator of the dataset's quality, guiding the setting of regularization hyperparameters. Furthermore, the derived upper bound fitting error links the back-propagated gradient, Neural Tangent Kernel (NTK), and the model's parameter count with the fitting error. Utilizing the triangle inequality, we establish an upper bound on the expected risk. This bound offers valuable insights into the effects of overparameterization, non-convex optimization, and the flat minima in DNNs.Finally, empirical verification confirms a significant positive correlation between the derived theoretical bounds and the practical expected risk, confirming the practical relevance of the theoretical findings.

When there's a major event that causes the destabilization of financial markets, not having a sound governance, risk and control (GRC) strategy for Machine Learning (ML) models becomes increasingly a risk to banks and other organizations. The pandemic is a prime example -- it sent shockwaves throughout the financial industry and jeopardized the validity of financial ML models. The current crisis in Ukraine is another example. As the conflict there worsens and the resulting economic fallout continues, the critical need for financial organizations to have checks in place to safeguard artificial intelligence (AI) and prevent bias will be revealed. You may have heard stories of grandparents trying to make their first-ever online purchases during the pandemic, only to be declined because they had never used their credit cards to shop online before the pandemic.

Biopharmaceutical manufacturing is a rapidly growing industry with impact in virtually all branches of medicine. Biomanufacturing processes require close monitoring and control, in the presence of complex bioprocess dynamics with many interdependent factors, as well as extremely limited data due to the high cost and long duration of experiments. We develop a novel model-based reinforcement learning framework that can achieve human-level control in low-data environments. The model uses a probabilistic knowledge graph to capture causal interdependencies between factors in the underlying stochastic decision process, leveraging information from existing kinetic models from different unit operations while incorporating real-world experimental data. We then present a computationally efficient, provably convergent stochastic gradient method for policy optimization. Validation is conducted on a realistic application with a multi-dimensional, continuous state variable.

In the biopharmaceutical manufacturing, fermentation process plays a critical role impacting on productivity and profit. Since biotherapeutics are manufactured in living cells whose biological mechanisms are complex and have highly variable outputs, in this paper, we introduce a model-based reinforcement learning framework accounting for model risk to support bioprocess online learning and guide the optimal and robust customized stopping policy for fermentation process. Specifically, built on the dynamic mechanisms of protein and impurity generation, we first construct a probabilistic model characterizing the impact of underlying bioprocess stochastic uncertainty on impurity and protein growth rates. Since biopharmaceutical manufacturing often has very limited data during the development and early stage of production, we derive the posterior distribution quantifying the process model risk, and further develop the Bayesian rule based knowledge update to support the online learning on underlying stochastic process. With the prediction risk accounting for both bioprocess stochastic uncertainty and model risk, the proposed reinforcement learning framework can proactively hedge all sources of uncertainties and support the optimal and robust customized decision making. We conduct the structural analysis of optimal policy and study the impact of model risk on the policy selection. We can show that it asymptotically converges to the optimal policy obtained under perfect information of underlying stochastic process. Our case studies demonstrate that the proposed framework can greatly improve the biomanufacturing industrial practice.

Biopharmaceutical manufacturing faces critical challenges, including complexity, high variability, lengthy lead time, and limited historical data and knowledge of the underlying system stochastic process. To address these challenges, we propose a green simulation assisted model-based reinforcement learning to support process online learning and guide dynamic decision making. Basically, the process model risk is quantified by the posterior distribution. At any given policy, we predict the expected system response with prediction risk accounting for both inherent stochastic uncertainty and model risk. Then, we propose green simulation assisted reinforcement learning and derive the mixture proposal distribution of decision process and likelihood ratio based metamodel for the policy gradient, which can selectively reuse process trajectory outputs collected from previous experiments to increase the simulation data-efficiency, improve the policy gradient estimation accuracy, and speed up the search for the optimal policy. Our numerical study indicates that the proposed approach demonstrates the promising performance.

The biomanufacturing industry is growing rapidly and becoming one of the key drivers of personalized medicine and life science. However, biopharmaceutical production faces critical challenges, including complexity, high variability, long lead time and rapid changes in technologies, processes, and regulatory environment. Driven by these challenges, we explore the biotechnology domain knowledge and propose a rigorous risk and sensitivity analysis framework for biomanufacturing innovation. Built on the causal relationships of raw material quality attributes, production process, and bio-drug properties in safety and efficacy, we develop a Bayesian Network (BN) to model the complex probabilistic interdependence between process parameters and quality attributes of raw materials/in-process materials/drug substance. It integrates various sources of data and leads to an interpretable probabilistic knowledge graph of the end-to-end production process. Then, we introduce a systematic risk analysis to assess the criticality of process parameters and quality attributes. The complex production processes often involve many process parameters and quality attributes impacting on the product quality variability. However, the real-world (batch) data are often limited, especially for customized and personalized bio-drugs. We propose uncertainty quantification and sensitivity analysis to analyze the impact of model risk. Given very limited process data, the empirical results show that we can provide reliable and inter-Corresponding author Email addresses: w.xie@northeastern.edu Thus, the proposed framework can provide the science-and risk-based guidance on the process monitoring, data collection, and process parameters specifications to facilitate the production process learning and stability control. Keywords: Decision analysis, biomanufacturing, Bayesian network, production process risk analysis, sensitivity analysis 2017 MSC: 00-01, 99-00 1. Introduction In the past decades, pharmaceutical companies have invested billions of dollars in the research and development (R&D) of new biomedicines for the treatment of many severe illnesses, including cancer cells and adult blindness. More than 40 percent of the overall pharmaceutical industry R&D and products in the development pipeline are biopharmaceuticals and this percentage is expected to continuously increase. Compared to the classical pharmaceutical manufacturing, biopharmaceutical production faces several challenges, including complexity, high variability, long lead time and rapid changes in technologies, processes, and regulatory environment (Kaminsky & Wang, 2015). Biotechnology products are produced in living organisms, which induces a lot of uncertainty in the production process.

The ability of machine learning models to read great quantities of unstructured data, spot patterns and translate it into actionable information is driving a significant uptake in the technology. Today, there is great interest in harnessing machine learning to turn the massive volumes of data – including non-traditional data – into new insights and information. In contrast to traditional statistical models, which are limited in the number of dimensions they can effectively access, machine learning models overcome these limitations and can ingest vast amounts of unstructured data, identify patterns and translate them into actionable information. It is therefore no surprise that machine learning modelling is being eagerly adopted. A recent survey conducted by SAS and the Global Association of Risk Professionals found that, over the next three to five years, businesses expect to significantly increase adoption of artificial intelligence (AI) and machine learning models to support key risk business use cases (see figure 1).

In recent years, artificial intelligence (AI) has moved from being fodder for post-apocalyptic fiction to occasionally dystopian reality. The technology has also enabled several valuable advances in consumer services. To date, AI's risks and benefits have remained largely limited to consumer-facing applications. And while the security and other unintended and unforeseen risks have affected many individuals and seem challenging to remediate, the causes--like cyberattacks, fake news, and privacy invasion--are increasingly well-understood. Over the last several years, however, AI and related technologies like decision intelligence (DI) have moved beyond Silicon Valley and Seattle to penetrate a new type of company: the large business enterprise.