According to one embodiment, a memory system includes a semiconductor memory and a controller. The semiconductor memory includes first blocks including a memory cell capable of storing data of one bit, a second block including a memory cell capable of storing data of two or more bits. The semiconductor memory stores first data in a first latch circuit, and second data in a second latch circuit, and writes the first data into one of the first blocks in page units, and the second data into one of the first blocks in page units. The semiconductor memory writes data of at least two pages into the second block, using the first data stored in the first latch circuit and the second data stored in the second latch circuit.

A method can include receiving a request to read data from a block of a memory device coupled with a processing device, determining, using a data structure mapping block identifiers to corresponding voltage distribution parameter values, a voltage distribution parameter value associated with the block of the memory device, determining a set of read levels associated with the voltage distribution parameter value, wherein each read level in the set of read levels corresponds to a respective voltage distribution of at least one memory cell comprised by the block, and reading, using the determined set of read levels, data from the block of the memory device.

Provided herein may be a memory system. The memory system may include a memory device including a memory block and a peripheral circuit, and a memory controller configured to transmit a program command based on a single-level cell scheme to the memory device so as to increase threshold voltages of the selection transistors included in the memory block after an erase operation has been performed on the memory block, and transmit, to the memory device, a read command to perform a check operation, wherein the read command indicates a first read voltage and a second read voltage higher than the first read voltage, and the check operation includes a check of whether the threshold voltages fall within a range between the first and second read voltages, or a check of whether the threshold voltages are lower than the first read voltage or higher than the second read voltage.

A non-volatile memory includes a cell array, a current supply circuit, a path selecting circuit and a judging circuit. The cell array includes plural multi-level memory cells in an mxn array. The cell array is connected with m word lines and n lines. The current supply circuit provides one of plural reference currents according to a current control value. The path selecting circuit is connected with the current supply circuit and the n bit lines. The judging circuit is connected with the path selecting circuit, and generates n output data. A first path selector of the path selecting circuit is connected with a path selecting circuit and a first bit line. A first judging device of the judging circuit is connected with the first path selector and generates a first output data.

A nonvolatile memory device including: a memory cell array, the memory cell array including a plurality of cell strings, at least one of the cell strings including a plurality of memory cells stacked in a direction perpendicular to a surface of a substrate, at least one of the memory cells is a multi-level cell storing at least three bits; and a control logic circuit configured to control a page buffer to read a fast read page of the memory cells with one read voltage and at least two normal read pages of the memory cells with the same number of read voltages.

A memory system includes a memory device, and a memory controller including a processor and an internal memory. A computer program including a neural network is stored in the memory system. The processor executes the computer program to extract a voltage level from each of a plurality of memory cells connected to one string select line (SSL), in which the memory cells and the SSL are included in a memory block of the memory device, provide the voltage levels as input to the neural network, and perform noise cancellation on the SSL, using the neural network, by changing at least one of the voltage levels from a first voltage level to a second voltage level. The first voltage level is classified into a first cluster of memory cells, and the second voltage level is classified into a second cluster of memory cells different from the first cluster.

A memory system is provided, including a semiconductor storage device including memory cells that can store data of n bits, and a word line connected to the cells; and a memory controller to control the device and being configured to send a first read request, in response to which the device can perform a first read operation of reading first data out of the cells with a first voltage applied to the word line, to send a second read request, in response to which the device can perform a second read operation of reading second data out of the cells with a second voltage within a first voltage range and a third voltage within a second voltage range applied to the word line, perform a first logical operation of logically processing the first and the second data, and send third data generated by the first logical operation to the controller.

Numerous embodiments are disclosed for compensating for differences in the slope of the current-voltage characteristic curve among reference transistors, reference memory cells, and flash memory cells during a read operation in an analog neural memory in a deep learning artificial neural network. In one embodiment, a method comprises receiving a first voltage, multiplying the first voltage by a coefficient to generate a second voltage, applying the first voltage to a gate of one of a reference transistor and a selected memory cell, applying the second voltage to a gate of the other of a reference transistor and a selected memory cell, and using the reference transistor in a sense operation to determine a value stored in the selected memory cell.

Numerous embodiments are disclosed for compensating for differences in the slope of the current-voltage characteristic curve among reference transistors, reference memory cells, and flash memory cells during a read operation in an analog neural memory in a deep learning artificial neural network. In one embodiment, a method comprises receiving a first voltage, multiplying the first voltage by a coefficient to generate a second voltage, applying the first voltage to a gate of one of a reference transistor and a selected memory cell, applying the second voltage to a gate of the other of a reference transistor and a selected memory cell, and using the reference transistor in a sense operation to determine a value stored in the selected memory cell.

A nonvolatile memory device including: a memory cell array, the memory cell array including a plurality of cell strings, at least one of the cell strings including a plurality of memory cells stacked in a direction perpendicular to a surface of a substrate, at least one of the memory cells is a multi-level cell storing at least three bits; and a control logic circuit configured to control a page buffer to read a fast read page of the memory cells with one read voltage and at least two normal read pages of the memory cells with the same number of read voltages.