Description:AS ATTACHED , Claims:I/We Claim:
1. Data stream (45) having a representation of a neural network (10) encoded
thereinto, wherein the data stream (45) comprises hierarchical control data
(400) structured into a 5 sequence (410) of control data portions (420),
wherein the control data portions (420) provide information on the neural
network at increasing details along the sequence of control data portions
(420).
10 2. Apparatus for encoding a representation of a neural network (10) into a data
stream (45), wherein the apparatus is configured to provide the data stream
(45) with hierarchical control data (400) structured into a sequence (410) of
control data portions (420), wherein the control data portions provide
information on the neural network at increasing details along the sequence
15 of control data portions.
3. Apparatus for decoding a representation of a neural network (10) from a
data stream (45), wherein the apparatus is configured to decode from the
data stream (45) hierarchical control data (400) structured into a sequence
20 (410) of control data portions (420), wherein the control data portions
provide information on the neural network at increasing details along the
sequence of control data portions.
4. Apparatus of claim 3, wherein at least some of the control data portions
25 (420) provide information on the neural network which is partially
redundant.
5. Apparatus of claim 3 or claim 4, wherein a first control data portion provides
the information on the neural network by way of indicating a default neural
30 network type implying default settings and a second control data portion
comprises a parameter to indicate each of the default settings.
62
6. Apparatus for performing an inference using a neural network, comprising
an apparatus for decoding a data stream (45) according to any of claims 3 to
5, so as to derive from the data stream (45) the neural network, and
a processor configured to perform 5 the inference based on the neural network.
7. Method for encoding a representation of a neural network into a data stream,
wherein the method comprises providing the data stream with hierarchical
control data structured into a sequence of control data portions, wherein the
10 control data portions provide information on the neural network at
increasing details along the sequence of control data portions.
8. Method for decoding a representation of a neural network from a data
stream, wherein the method comprises decoding from the data stream
15 hierarchical control data structured into a sequence of control data portions,
wherein the control data portions provide information on the neural network
at increasing details along the sequence of control data portions.
9. Computer program for, when executed by a computer, causing the computer
20 to perform the method of claim 7 or claim 8