Abstract: A video encoder is configured to entropy encode an absolute value of a quantization level of a current transform coefficient at position (xC, yC), wherein the absolute value is encoded using context adaptive binary arithmetic encoding of bins of a first binarization. The video coder is further configured, for the current transform coefficient, to encode a bin of the first binarization by using a context which is determined based on a sum of minimum absolute values of transform coefficient quantization levels, based on encoded bins of the first binarization, at one or more transform coefficient positions among (xC+1, yC), (xC+2, yC), (xC+1, yC+1), (xC, yC+1), and (xC, yC+2).

Abstract: Embodiments according to the invention comprise an apparatus for decoding neural network parameters, which define a neural network. The apparatus may, optionally, be configured to obtain, e.g. to decode, parameters of a base model, e.g. NB, of the neural network which define one or more layers, e.g. base layers, of the neural network. Furthermore, the apparatus is configured to decode an update model, e.g. NU1 to NUK, which defines a modification of one or more layers, e.g. base layers, of the neural network, and the apparatus is configured modify parameters of a base model of the neural network using the update model, in order to obtain an updated model, e.g. designated as “new model” comprising new model layers LNkj. Moreover, the apparatus is configured to evaluate a skip information, e.g. a skip_row_flag and/or a skip_column_flag, indicating whether a sequence, e.g. a row, or a column or a block, of parameters of the update model is zero or not.

Abstract: Disclosed is a decoder for decoding parameters of a neural network, configured to obtain a plurality of neural network parameters of the neural network on the basis of an encoded bitstream, to obtain, e.g. to receive; e.g. to extract from an encoded bitstream, a node information describing a node of a parameter update tree, wherein the node information has a parent node identifier, which is, for example, a unique parent node identifier, for example an integer number, a string, and/or a cryptographic hash, and wherein the node information has a parameter update information, e.g. one or more update instructions, for example a difference signal between initial neural network parameters and a newer version thereof, e.g. corresponding to a child node of the update tree, and to derive one or more neural network parameters using parameter information of a parent node identified by the parent node identifier and using the parameter update information.

Abstract: A video encoder is configured to entropy encode an absolute value of a quantization level of a current transform coefficient at position (xC, yC), wherein the absolute value is encoded using context adaptive binary arithmetic encoding of bins of a first binarization. The video coder is further configured, for the current transform coefficient, to encode a bin of the first binarization by using a context which is determined based on a sum of minimum absolute values of transform coefficient quantization levels, based on encoded bins of the first binarization, at one or more transform coefficient positions among (xC+1, yC), (xC+2, yC), (xC+1, yC+1), (xC, yC+1), and (xC, yC+2).

Abstract: The invention describes an encoding scheme for arithmetically encoding a sequence of information values into an arithmetic coded bitstream using providing the bitstream with entry point information allowing for resuming arithmetic decoding the bitstream from a predetermined entry point onward. A respective decoding scheme is also provided. These encoding and decoding schemes provide more efficient encoding concept in view of the decoding speed.

Abstract: A video encoder is configured to entropy encode an absolute value of a quantization level of a current transform coefficient at position (xC, yC), wherein the absolute value is encoded using context adaptive binary arithmetic encoding of bins of a first binarization. The video coder is further configured, for the current transform coefficient, to encode a bin of the first binarization by using a context which is determined based on a sum of minimum absolute values of transform coefficient quantization levels, based on encoded bins of the first binarization, at one or more transform coefficient positions among (xC+1, yC), (xC+2, yC), (xC+1, yC+1), (xC, yC+1), and (xC, yC+2).

Abstract: A decoder for decoding weight parameters of a neural network, wherein the decoder is configured to obtain a plurality of neural network parameters of the neural network on the basis of an encoded bitstream. Furthermore, the decoder is configured to decode the neural network parameters of the neural network using a context-dependent arithmetic decoding Moreover, the decoder is configured to obtain a probability estimate for a decoding of a bin of a number representation of a neural network parameter using one or more probability estimation parameters. In addition, the decoder is configured to use different probability estimation parameter values for a decoding of different neural network parameters and/or to use different probability estimation parameter values for a decoding of bins associated with different context models. Some embodiments are configured to use different probability estimation parameter values for a decoding of neural network parameters of different layers of the neural network.

Abstract: An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

Abstract: The invention describes an encoding scheme for encoding a sequence of integer values, particularly by first using encoding a value at a predetermined position and then consecutively calculating and encoding differences between neighboring values. A respective decoding scheme is also provided. These encoding and decoding schemes provide a more efficient encoding concept.

Abstract: An encoder encodes transform coefficients of a transform coefficient block representing a block of a picture using a scan pattern which sequentially traverses the transform coefficients of the transform block by encoding absolute values of quantization levels of the transform coefficients. The absolute values are binarized with a binarization comprising a first part of the binarization below a cutoff value and a second part of the binarization, prefixed by a codeword of the first part of the binarization for the cutoff value, above the cutoff value. The encoder adaptively, based on previously encoded transform coefficients, decreases the cutoff value to zero monotonically during encoding of the transform coefficients so that the binarization comprises the second part of the binarization and not the first part of the binarization.

Abstract: Apparatus for generating a NN representation, configured to quantize an NN parameter onto a quantized value by determining a quantization parameter and a quantization value for the NN parameter so that from the quantization parameter, there is derivable a multiplier and a bit shift number. Additionally, the determining of the quantization parameter and the quantization value for the NN parameter is performed so that the quantized value of the NN parameter corresponds to a product between the quantization value and a factor, which depends on the multiplier, bit-shifted by a number of bits which depends on the bit shift number.

Abstract: A video decoder decodes a first indication (190) indicating whether transform coefficients of a first transform coefficient block (921) corresponding to a first color component are encoded into a data stream. The decoder also decodes a second indication (190) indicating whether transform coefficients of a second transform coefficient block (922) corresponding to a second color component are encoded into the data stream using context-adaptive entropy decoding with a context selected based on the first indication for the first transform coefficient block (921). The decoder further derives a block (84) of the picture by, separately for the first color component and the second color component, a reverse transformation of the first transform coefficient block (921 and the second transform block (922, respectively.

Abstract: Embodiments according to a first aspect of the present invention are based on the idea, that neural network parameters may be compressed more efficiently by using a non-constant quantizer, but varying same during coding the neural network parameters, namely by selecting a set of reconstruction levels depending on quantization indices decoded from, or respectively encoded, into the data stream for previous or respectively previously encoded neural network parameters. Embodiments according to a second aspect of the present invention are based on the idea that a more efficient neural network coding may be achieved when done in stages—called reconstruction layers to distinguish them from the layered composition of the neural network in neural layers—and if the parametrizations provided in these stages are then, neural network parameter-wise combined to yield a neural network parametrization improved compared to any of the stages.

Abstract: A decoder configured to decode residual levels, and sequentially dequantize the residual levels by selecting a quantizer out of a set of default quantizers depending on a current transition state, and updating the current transition state depending on a current residual level's characteristic obtained by an application of a binary function onto the current residual level, and depending on a quantization mode information contained in the data stream. The current transition state transitions, according to a surjective mapping which depends on the quantization mode information, from a domain of combinations of a set of one or more transition states with the current residual level's characteristic onto the set of one or more transition states, wherein a cardinality of the set of one or more transition states differs depending on the quantization mode information.

Abstract: An arithmetic encoder for encoding a plurality of symbols having symbol values is configured to derive an interval size information for an arithmetic encoding of one or more symbol values to be encoded based on a plurality of state variable values representing statistics of a plurality of previously encoded symbol values with different adaptation time constants. The arithmetic encoder is configured to map a first state variable value, or a scaled and/or rounded version thereof, using a lookup-table and to map a second state variable value, or a scaled and/or rounded version thereof using the lookup-table, in order to obtain the interval size information describing an interval size for the arithmetic encoding of one or more symbols to be encoded. Further arithmetic encoders, arithmetic decoders, video encoders, video decoder, methods for encoding, methods for decoding and computer programs are also disclosed which are based on the same concept and on other concepts.

Abstract: A method for manufacturing a semiconductor transistor device includes etching a vertical gate trench into a silicon region, depositing a silicon gate material on an interlayer dielectric formed in the vertical gate trench so that an upper side of the interlayer dielectric is covered, etching through the silicon gate material in the vertical gate trench to partly uncover the upper side of the interlayer dielectric and so that a silicon gate region of a gate electrode of the semiconductor transistor device remains in the vertical gate trench, and depositing a metal material into the vertical gate trench so that the partly uncovered upper side of the interlayer dielectric is covered by the metal material.

Abstract: A semiconductor device includes: a semiconductor substrate; trenches formed in the substrate and extending lengthwise in parallel with one another, the trenches having connecting regions which interconnect adjacent ones of the trenches; semiconductor mesas separated from one another by the trenches in a first lateral direction and by the connecting regions in a second lateral direction transverse to the first lateral direction; a gate electrode and a field electrode below the gate electrode in at least some of the trenches, and dielectrically insulated from each other and from the semiconductor substrate; first contacts vertically extending into one or more transistor device regions in the semiconductor mesas; and second contacts vertically extending into the field electrodes in the connecting regions such that the gate electrodes are uninterrupted by the second contacts. Corresponding methods of producing such a semiconductor device are also described.

Abstract: Data stream having a representation of a neural network encoded thereinto, the data stream including serialization parameter indicating a coding order at which neural network parameters, which define neuron interconnections of the neural network, are encoded into the data stream.

Abstract: A transistor device with a gate electrode in a vertical gate trench is described. The gate electrode includes a silicon gate region and a metal inlay region. The silicon gate region forms at least a section of a sidewall of the gate electrode. The metal inlay region extends up from a lower end of the gate electrode.

Abstract: A semiconductor device includes: a semiconductor substrate; trenches formed in the substrate and extending lengthwise in parallel with one another, the trenches having connecting regions which interconnect adjacent ones of the trenches; semiconductor mesas separated from one another by the trenches in a first lateral direction and by the connecting regions in a second lateral direction transverse to the first lateral direction; a gate electrode and a field electrode below the gate electrode in at least some of the trenches, and dielectrically insulated from each other and from the semiconductor substrate; first contacts vertically extending into one or more transistor device regions in the semiconductor mesas; and second contacts vertically extending into the field electrodes in the connecting regions such that the gate electrodes are uninterrupted by the second contacts. Corresponding methods of producing such a semiconductor device are also described.