Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a source area, a channel area, a gate electrode, and a drain area. The channel area may include a first channel region with a dopant of a first concentration next to the source area, and a second channel region with the dopant of a second concentration higher than the first concentration next to the drain area. A source electrode may be in contact with the source area, a gate oxide layer above the channel area, and the gate electrode above the gate oxide layer. A first resistance exists between the source electrode and the gate electrode. A second resistance exists between the source electrode, the gate electrode, and a path through the gate oxide layer to couple the source electrode and the gate electrode after a programming operation is performed. Other embodiments may be described and/or claimed.

Abstract: A heterogeneous integration semiconductor package structure including a heat dissipation assembly, multiple chips, a package assembly, multiple connectors and a circuit substrate is provided. The heat dissipation assembly has a connection surface and includes a two-phase flow heat dissipation device and a first redistribution structure layer embedded in the connection surface. The chips are disposed on the connection surface of the heat dissipation assembly and electrically connected to the first redistribution structure layer. The package assembly surrounds the chips and includes a second redistribution structure layer disposed on a lower surface and multiple conductive vias electrically connected to the first redistribution structure layer and the second redistribution structure layer. The connectors are disposed on the package assembly and electrically connected to the second redistribution structure layer.

Abstract: An ear tag module includes a rod member, a spike, a circuit component, and a temperature sensor. The spike is disposed on one side of the rod member, and the circuit component is disposed on another side of the rod member. The temperature sensor is electrically connected to the circuit component. When the spike penetrates an ear, the ear is in contact with a sensing area of the rod member, and the temperature sensor is located in the rod member to detect a temperature of the ear and transmit at least one temperature sensing information to the circuit component.

Abstract: An analog multiplication circuit includes switched capacitors to multiply digital operands in an analog representation and output a digital result with an analog-to-digital convertor. The capacitors are arranged with a capacitance according to the respective value of the digital bit inputs. To perform the multiplication, the capacitors are selectively charged according to the first operand of the multiplication. The capacitors are then connected to a common interconnect for charge sharing across the capacitors, averaging the charge according to the charge determined by the first operand. The capacitor are then maintained or discharged according to a second operand, such that the remaining charge represents a number of “copies” of the averaged charge. The capacitors are then averaged and output for conversion by an analog-to-digital convertor. This circuit may be repeated to construct a multiply-and-accumulate circuit by combining charges from several such multiplication circuits.

Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a semiconductor well, a source area and a drain area next to the semiconductor well, a gate electrode, and a base terminal. The gate electrode may be coupled to the base terminal, hence forming a floating body MOSFET. A junction may exist between the drain area and the semiconductor well. A first resistance may exist between the source area and the drain area through the semiconductor well. A programming operation may be performed when the gate electrode is coupled to a high impedance, a programming voltage is applied at the source area, and the drain area is coupled to a ground voltage to break the junction between the drain area and the semiconductor well to generate a current between the source area, the semiconductor well, and the drain area. Other embodiments may be described and/or claimed.

Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a source area, a channel area, a gate electrode, and a drain area. The channel area may include a first channel region with a dopant of a first concentration next to the source area, and a second channel region with the dopant of a second concentration higher than the first concentration next to the drain area. A source electrode may be in contact with the source area, a gate oxide layer above the channel area, and the gate electrode above the gate oxide layer. A first resistance exists between the source electrode and the gate electrode. A second resistance exists between the source electrode, the gate electrode, and a path through the gate oxide layer to couple the source electrode and the gate electrode after a programming operation is performed. Other embodiments may be described and/or claimed.

Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a source area, a channel area, a gate electrode, and a drain area. The channel area may include a first channel region with a dopant of a first concentration next to the source area, and a second channel region with the dopant of a second concentration higher than the first concentration next to the drain area. A source electrode may be in contact with the source area, a gate oxide layer above the channel area, and the gate electrode above the gate oxide layer. A first resistance exists between the source electrode and the gate electrode. A second resistance exists between the source electrode, the gate electrode, and a path through the gate oxide layer to couple the source electrode and the gate electrode after a programming operation is performed. Other embodiments may be described and/or claimed.

Abstract: Systems and methods for precision writing of weight values to a memory capable of storing multiple levels in each cell are disclosed. Embodiments include logic to compare an electrical parameter read from a memory cell with a base reference and an interval reference, and stop writing once the electrical parameter is between the base reference and the base plus the interval reference. The interval may be determined using a greater number of levels than the number of stored levels, to prevent possible overlap of read values of the electrical parameter due to memory device variations.

Abstract: An ear tag module includes a rod member, a spike, a circuit component, and a temperature sensor. The spike is disposed on one side of the rod member, and the circuit component is disposed on another side of the rod member. The temperature sensor is electrically connected to the circuit component. When the spike penetrates an ear, the ear is in contact with a sensing area of the rod member, and the temperature sensor is located in the rod member to detect a temperature of the ear and transmit at least one temperature sensing information to the circuit component.

Abstract: A plug-in type power module includes a power unit and a heat-transfer unit vertically disposed on the power unit and extending outwardly away from two sides of the power unit. A first ceramic layer is disposed between the power unit and the heat-transfer unit. Therefore, heat generated by the power unit can be transferred from the first ceramic layer to the heat-transfer unit to increase the speed of heat dissipation. A subsystem having the plug-in type power module is also provided.

Abstract: A plug-in type power module includes a power unit and a heat-transfer unit vertically disposed on the power unit and extending outwardly away from two sides of the power unit. A first ceramic layer is disposed between the power unit and the heat-transfer unit. Therefore, heat generated by the power unit can be transferred from the first ceramic layer to the heat-transfer unit to increase the speed of heat dissipation. A subsystem having the plug-in type power module is also provided.

Abstract: A plug-in type power module includes a power unit and a heat-transfer unit vertically disposed on the power unit and extending outwardly away from two sides of the power unit. A first ceramic layer is disposed between the power unit and the heat-transfer unit. Therefore, heat generated by the power unit can be transferred from the first ceramic layer to the heat-transfer unit to increase the speed of heat dissipation. A subsystem having the plug-in type power module is also provided.

Abstract: A method for compressing an initial weight matrix includes generating a first weight matrix and a second weight matrix according to the initial weight matrix where the initial weight matrix is a Kronecker product of a transposed matrix of the second weight matrix and the first weight matrix; optimizing the first and second weight matrixes to generate an optimized first weight matrix and an optimized second weight matrix; generating a processed data matrix according to an initial data matrix where the initial data matrix is vectorization of the processed data matrix; multiplying the processed data matrix by the optimized first weight matrix to generate a first product; multiplying the optimized second weight matrix by the first product to generate a second product; and vectorizing the second product. The initial weight matrix requires a larger memory space than a combined memory space of the first and second weight matrixes.

Abstract: A method for compressing an initial weight matrix includes generating a first weight matrix and a second weight matrix according to the initial weight matrix where the initial weight matrix is a Kronecker product of a transposed matrix of the second weight matrix and the first weight matrix; optimizing the first and second weight matrixes to generate an optimized first weight matrix and an optimized second weight matrix; generating a processed data matrix according to an initial data matrix where the initial data matrix is vectorization of the processed data matrix; multiplying the processed data matrix by the optimized first weight matrix to generate a first product; multiplying the optimized second weight matrix by the first product to generate a second product; and vectorizing the second product. The initial weight matrix requires a larger memory space than a combined memory space of the first and second weight matrixes.

Abstract: A gesture recognition system includes a Frequency modulated continuous waveform radar system. First and second channels of the signal reflected by the object are preprocessed and respectively sent to first and second feature map generators. A machine-learning accelerator is configured to receive output from the first and second feature map generators and form frames fed to a deep neural network realized with a hardware processor array for gesture recognition. A memory stores a compressed set of weights as fixed-point, low rank matrices that are directly treated as weights of the deep neural network during inference.

Abstract: A power module including a plurality of substrates, a plurality of power devices, and a heat dissipation assembly is provided. The substrates are located on different planes and surround an axis. Each of the substrates extends along the axis. The power devices electrically connected with each other are disposed on the substrates respectively. The heat dissipation assembly is disposed on the substrates and opposite to the power devices. Heat generated from the power devices is transferred to the heat dissipation assembly through the substrates.

Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a semiconductor well, a source area and a drain area next to the semiconductor well, a gate electrode, and a base terminal. The gate electrode may be coupled to the base terminal, hence forming a floating body MOSFET. A junction may exist between the drain area and the semiconductor well. A first resistance may exist between the source area and the drain area through the semiconductor well. A programming operation may be performed when the gate electrode is coupled to a high impedance, a programming voltage is applied at the source area, and the drain area is coupled to a ground voltage to break the junction between the drain area and the semiconductor well to generate a current between the source area, the semiconductor well, and the drain area. Other embodiments may be described and/or claimed.

Abstract: Embodiments herein may describe techniques for an integrated circuit including a MOSFET having a source area, a channel area, a gate electrode, and a drain area. The channel area may include a first channel region with a dopant of a first concentration next to the source area, and a second channel region with the dopant of a second concentration higher than the first concentration next to the drain area. A source electrode may be in contact with the source area, a gate oxide layer above the channel area, and the gate electrode above the gate oxide layer. A first resistance exists between the source electrode and the gate electrode. A second resistance exists between the source electrode, the gate electrode, and a path through the gate oxide layer to couple the source electrode and the gate electrode after a programming operation is performed. Other embodiments may be described and/or claimed.

Abstract: A design method of an assistive device and an electronic system of assistive device design are provided. The design method of the assistive device are adapted for an electronic devices including a processor. The design method includes: obtaining a point cloud data of a limb part; determining a plurality of reference cross sections according to the point cloud data, wherein each of the reference cross sections is determined corresponding to bone protrusion feature points of the point cloud data, wherein the bone protrusion feature points are corresponding to the bony prominences of the limb parts respectively; establishing an initial digital model of the assistive device according to the reference cross sections; and performing a structural simulation analysis according to the initial digital model and design limitations to obtain a product digital model of the assistive device.

Abstract: A performing device of a gesture recognition system executes a performing procedure of a gesture recognition method. The performing procedure includes steps of: receiving a sensing signal; selecting one of sensing frames of the sensing signal; determining a soft label of the selected sensing frame; classifying a gesture event when the soft label of the selected sensing frame is approved. The gesture event is classified to determine the motion of the user. Therefore, the gesture recognition system does not need a predetermined time period to recognize the motion of the user. The time period for recognizing the motion of the user can be dynamical. A total time period for classifying a plurality of motions can be decreased, and the performance of the gesture recognition system can be improved.