Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: An ensemble learning based method is for a binary classification on an imbalanced dataset. The imbalanced dataset has a minority class comprising positive samples and a majority class comprising negative samples. The method includes: generatively oversampling the imbalanced dataset by synthetically generating minority class examples, thereby generating a generated dataset; using the generated dataset to generate subsamples, and learning a base classifier on each of the subsamples to determine a plurality of base classifiers; and learning a weighted majority vote classifier by combining outputs of the base classifiers. Each of the base classifiers is assigned a weight in such a way that a diversity between the base classifiers on the positive samples is minimized.

Abstract: An ensemble learning based method is for a binary classification on an imbalanced dataset. The imbalanced dataset has a minority class comprising positive samples and a majority class comprising negative samples. The method includes: generatively oversampling the imbalanced dataset by synthetically generating minority class examples, thereby generating a generated dataset; using the generated dataset to generate subsamples, and learning a base classifier on each of the subsamples to determine a plurality of base classifiers; and learning a weighted majority vote classifier by combining outputs of the base classifiers. Each of the base classifiers is assigned a weight in such a way that a diversity between the base classifiers on the positive samples is minimized.

Abstract: An ensemble learning based method is for a binary classification on an imbalanced dataset. The imbalanced dataset has a minority class comprising positive samples and a majority class comprising negative samples. The method includes: generatively oversampling the imbalanced dataset by synthetically generating minority class examples, thereby generating a generated dataset; using the generated dataset to generate subsamples, and learning a base classifier on each of the subsamples to determine a plurality of base classifiers; and learning a weighted majority vote classifier by combining outputs of the base classifiers. Each of the base classifiers is assigned a weight in such a way that a diversity between the base classifiers on the positive samples is minimized.

Abstract: The present disclosure describes a method, system, and a computer readable medium for extracting tabular data present in a document. The method comprises detecting presence of at least one table in the document using a deep learning based model and a statistical method. The method further comprises identifying a type of the table based on determining a count of horizontal and vertical lines, presence of outer borders, and presence of row-column intersections in the table. The type of the table comprises a bordered table, a partially bordered table, or a borderless table. The method further comprises processing the detected table, depending on its type, to identify one or more cells present in the table. The method further comprises generating an output file by extracting the tabular data present in the table, where the extracting comprises performing optical character recognition on the identified one or more cells.

Abstract: The present disclosure describes a method, system, and a computer readable medium for extracting tabular data present in a document. The method comprises detecting presence of at least one table in the document using a deep learning based model and a statistical method. The method further comprises identifying a type of the table based on determining a count of horizontal and vertical lines, presence of outer borders, and presence of row-column intersections in the table. The type of the table comprises a bordered table, a partially bordered table, or a borderless table. The method further comprises processing the detected table, depending on its type, to identify one or more cells present in the table. The method further comprises generating an output file by extracting the tabular data present in the table, where the extracting comprises performing optical character recognition on the identified one or more cells.

Abstract: An ensemble learning based method is for a binary classification on an imbalanced dataset. The imbalanced dataset has a minority class comprising positive samples and a majority class comprising negative samples. The method includes: generatively oversampling the imbalanced dataset by synthetically generating minority class examples, thereby generating a generated dataset; using the generated dataset to generate subsamples, and learning a base classifier on each of the subsamples to determine a plurality of base classifiers; and learning a weighted majority vote classifier by combining outputs of the base classifiers. Each of the base classifiers is assigned a weight in such a way that a diversity between the base classifiers on the positive samples is minimized.

Abstract: A method for decentralized multi-task learning includes publishing metadata associated with a first task. A plurality of parameter vectors associated with a set of similar tasks to the first task is obtained and the set of similar tasks is associated with a plurality of other participants. A parameter vector associated with a machine learning dataset for the first task is trained based on a loss function associated with the first task and the plurality of parameter vectors associated with the set of similar tasks. The parameter vector associated with the machine learning dataset for the first task is published.

Abstract: A method for lifelong machine learning using boosting includes receiving a new task and a learning sample for the new task. A distribution of weights is learned over the learning sample using previously learned classifiers from old tasks. A set of task-specific classifiers are learned for the new task using a boosting algorithm and the distribution of weights over the learning sample, whereby the distribution of weights over the learning sample is updated using the task-specific classifiers for the new task.

Abstract: A cache system for a storage device includes a solid state drive (SSD), a random access memory (RAM), and a cache control device. The cache control device is configured to: retrieve data from the storage device in response to a request to read data from the storage device, store at least some of the data in one or both of (i) the SSD and (ii) the RAM, when storing the at least some of the data to the RAM, write to the RAM non-sequentially with respect to a memory space of the RAM, and when storing the at least some of the data in the SSD, write to the SSD sequentially with respect to a memory space of the SSD. The cache control device comprises an SSD interface device configured to allocate memory for storing data in the SSD sequentially with respect to the memory space of the SSD.

Abstract: A cache system for a storage device includes a solid state drive (SSD), a random access memory (RAM), and a cache control device. The cache control device is configured to: retrieve data from the storage device in response to a request to read data from the storage device, store at least some of the data in one or both of (i) the SSD and (ii) the RAM, when storing the at least some of the data to the RAM, write to the RAM non-sequentially with respect to a memory space of the RAM, and when storing the at least some of the data in the SSD, write to the SSD sequentially with respect to a memory space of the SSD. The cache control device comprises an SSD interface device configured to allocate memory for storing data in the SSD sequentially with respect to the memory space of the SSD.

Abstract: A cache system for a storage device includes (i) one or more solid state drives (SSDs), (ii) one or more random access memories (RAMs), and (iii) a cache control device. The cache control device caches at least some of first data that is to be written to the storage device, and caches at least some of second data that is retrieved from the storage device. When caching first data or second data in one of the one or more RAMs, the cache control device writes to the one RAM non-sequentially with respect to a memory space of the one RAM. When caching first data or second data in one of the one or more SSDs, the cache control device writes to the one SSD sequentially with respect to a memory space of the one SSD.

Abstract: This disclosure describes a network system that provides media content to a user. The user may become stimulated by the media content and desire to receive information about the media content that stimulated the user's interest. This disclosure describes techniques providing information regarding events within the media content that stimulated the user's interest, i.e., stimuli information.

Abstract: A system including a storage processing device with an input/output module. The input/output module has port processors to receive and transmit network traffic. The input/output module also has a switch connecting the port processors. Each port processor categorizes the network traffic as fast path network traffic or control path network traffic. The switch routes fast path network traffic from an ingress port processor to a specified egress port processor. The storage processing device also includes a control module to process the control path network traffic received from the ingress port processor. The control module routes processed control path network traffic to the switch for routing to a defined egress port processor. The control module is connected to the input/output module. The input/output module and the control module are configured to interactively support data virtualization, data migration, data replication, and snapshotting.

Abstract: A system including a storage processing device with an input/output module. The input/output module has port processors to receive and transmit network traffic. The input/output module also has a switch connecting the port processors. Each port processor categorizes the network traffic as fast path network traffic or control path network traffic. The switch routes fast path network traffic from an ingress port processor to a specified egress port processor. The storage processing device also includes a control module to process the control path network traffic received from the ingress port processor. The control module routes processed control path network traffic to the switch for routing to a defined egress port processor. The control module is connected to the input/output module. The input/output module and the control module are configured to interactively support data virtualization, data migration, data journaling, and snapshotting.

Abstract: A method for generating electricity in which sludge is anaerobically digested to form a gas mixture of methane and carbon dioxide and a residue of digested sludge. Water is removed from the digested sludge to form dewatered sludge, which, in turn, is gasified to form a gaseous composition which includes carbon monoxide and hydrogen. The gas mixture containing methane and carbon dioxide produced in the anaerobic digestion step is mixed with the gas mixture containing hydrogen and carbon monoxide from the gasification step and burned in an apparatus, such as a micro-turbine, for generating electricity. The non-carbonaceous fraction of the sludge is melted during the gasification step and rendered environmentally benign.

Abstract: A method for stabilization of liquid mercury in which powdered copper particles are cleaned with a chemically reactive fluid suitable for removing surface oxidation from the surface. “Clean” powdered copper particles are mixed with liquid mercury to form a powdered copper/liquid mercury mixture. The mixture is then hardened to form an amalgam. Amalgams in which the amount of mercury is greater than 50% by weight of the total amalgam may be produced in accordance with the method of this invention.

Abstract: Bioprocesses are disclosed for the production of compounds which can be produced from a dipeptide intermediate. The process comprises production of a recombinant polypeptide which contains the dipeptide intermediate. The dipeptide intermediate is further processed to ultimately provide the finished product.