Abstract: A coprocessor of a processing device used to perform pooling operations. The disclosed coprocessor, among other things, receives an activation tensor of a neural network model. The coprocessor applies a pooling window to the activation tensor. The coprocessor reads, from a memory device, a plurality of memory locations. For each memory location, the coprocessor stores a value from a respective memory location associated with a channel of the activation tensor to a corresponding buffer of a set of buffers. Responsive to determining a number of values in each buffer of the set of buffers matches a number of values within the pooling window applied to the activation tensor performing, for each buffer using its values, a pooling operation.

Abstract: Implementations disclosed describe methods and systems to perform the methods of deploying and executing machine learning models on target-specific computational platforms. Optimization techniques include but are not limited to alignment of kernel operations with hardware instructions of a target processing device, reduction of kernel dimensions near boundaries of data, efficient reuse of a small number of memory components during neural network operations, run-time quantization of data and neural network parameters, and other methods.

Abstract: The present disclosure relates to a sensor arrangement (1) for analyzing substances in a material, comprising a substrate (2), a first reception area (5) for receiving a first material, an electronic component sensor (3), a test area (4) that is in contact with the electronic component sensor (3), and a control device (10). The first reception area (5) and the test area (4) are arranged on the substrate (2). The control device (10) is configured for controlling the first reception area (5) and/or the test area (4) to move a portion of the first material from the first reception area (5) into the test area (4). Further, the present disclosure relates to a method for operating such a sensor arrangement (1).

Abstract: The present disclosure relates to a sensor arrangement (1) for analyzing substances in a material, comprising a substrate (2), a first reception area (5) for receiving a first material, an electronic component sensor (3), a test area (4) that is in contact with the electronic component sensor (3), and a control device (10). The first reception area (5) and the test area (4) are arranged on the substrate (2). The control device (10) is configured for controlling the first reception area (5) and/or the test area (4) to move a portion of the first material from the first reception area (5) into the test area (4). Further, the present disclosure relates to a method for operating such a sensor arrangement (1).

Abstract: The invention relates to a device (100; 200; 300; 400) for analyzing biological substances in a test solution, comprising a test substrate (101; 203; 303; 401) which is transparent at least in part, having a test region (107a, 108a, 109a, 110a; 211; 411) for receiving the test solution, a plurality of electrodes (111, 106; 201, 202; 301, 302; 402, 403) which are arranged on the test substrate (101; 203; 303; 401) and extend into the test region (107a, 108a, 109a, 110a; 211; 411), wherein in each case, at least one portion of the electrodes (111, 106; 201, 202; 301, 302; 402, 403) is made of a transparent material.

Abstract: The invention relates to a device (100; 200; 300; 400) for analysing biological substances in a test solution, comprising a test substrate (101; 203; 303; 401) which is transparent at least in part, having a test region (107a, 108a, 109a, 110a; 211; 411) for receiving the test solution, a plurality of electrodes (111, 106; 201, 202; 301, 302; 402, 403) which are arranged on the test substrate (101; 203; 303; 401) and extend into the test region (107a, 108a, 109a, 110a; 211; 411), wherein in each case, at least one portion of the electrodes (111, 106; 201, 202; 301, 302; 402, 403) is made of a transparent material.