In representative embodiments, systems and methods to calculate the likelihood that presented cryptographic key material is untrustworthy are disclosed. A predictive model based on a debasing condition and a dataset is created by evaluating the dataset relative to the debasing condition. For example, if certificate revocation is selected as the debasing condition, the dataset is analyzed to produce a predictive model that determines the likelihood that a presented certificate is untrustworthy based on similarity to already revoked certificates. The predictive model can include a supervised learning model like a logistic regression model or a deep neural network model. The system can be used in conjunction with existing security infrastructures or can be used as a separate infrastructure. Based on the likelihood score calculated by the model, a relying system can reject the cryptographic key material, accept the cryptographic key material or take other further action.

One or more computer processors are used to train a reinforcement learning machine learning model, such as a contextual bandit machine learning model. A training dataset is inputted to the reinforcement learning machine learning model. The reinforcement learning machine learning model is trained based on the training dataset. During the training, an entropy of the reinforcement learning machine learning model is determined. Based on the feedback, feedback is generated. The reinforcement learning machine learning model is further trained based on the feedback.

Methods for classification of microblogs using semi-supervised open domain targeted sentiment classification. A hidden Markov model support vector machine (SVM HMM) is trained with a training dataset combined with discrete features. A portion of the training dataset is clustered by k-means clustering to generate cluster IDs which are normalized and combined with the discrete features. After formatting, the combined dataset is applied to the SVM HMM and the C parameter, which is optimized by calculating a zero-one error at each iteration. The open domain targeted sentiment classification methods uses less labelled data than previous sentiment analysis techniques, thus decreasing processing costs. Additionally, a supervised learning model for improving the accuracy of open domain targeted sentiment classification is presented using an SVM HMM.

A method of detecting and diagnosing cancers characterized by the presence of at least one nodule/neoplasm from an imaging scan is presented. To detect nodules in an imaging scan, a 3D CNN using a single feed forward pass of a single network is used. After detection, risk stratification is performed using a supervised or an unsupervised deep learning method to assist in characterizing the detected nodule/neoplasm as benign or malignant. The supervised learning method relies on a 3D CNN used with transfer learning and a graph regularized sparse MTL to determine malignancy. The unsupervised learning method uses clustering to generate labels after which label proportions are used with a novel algorithm to classify malignancy. The method assists radiologists in improving detection rates of lung nodules to facilitate early detection and minimizing errors in diagnosis.