Methods and systems for generating an integer neural network are described. The method includes receiving an input vector comprising a plurality of input values. The plurality of input values are represented using a desired number bits. The input vector is multiplied by a weight vector, and the products of which are summed to obtain a first value. The first value is quantized and applied to a piecewise linear activation function to obtain a second value. The piecewise linear activation function is a set of linear function that collectively approximate a nonlinear activation function. The second value is quantized to generate the output of the neuron in the integer neural network.

A biodegradable bi-component fiber may include a polyhydroxyalkanoate and/or polylactic acid with cellulose acetate and/or plasticized cellulose acetate for use in a filter material configured for use in a filter of a smoking article. The bi-component fiber may have a sheath-core construction where one component of the bi-component forms the core, and the other component forms the sheath of each fiber. A filter made in accordance with this design may also include non-biodegradable material.

Provided is a tobacco sheet for non-combustion heating type flavor inhalers, which has high bulkiness. The tobacco sheet for non-combustion heating type flavor inhalers contains a fibrous material.

Disclosed are fibers comprising one or more branded fibers which exhibit surface markings in a repeated pattern along the length of the branded fibers. The branded fibers can be incorporated into yarns or fiber bands to represent supply chain information of the yarns, fiber bands, and/or articles made from the yards or fiber bands. In a specific example, branded fibers can be incorporated into an acetate tow band The branded fibers can be recovered from a cigarette filter, the repeated pattern decoded, and supply chain information associated with the acetate tow used to make the cigarette filter, such as manufacturer, customer, ship to location, and even the acetate tow bale, can be obtained.

A biodegradable bi-component fiber may include a polyhydroxyalkanoate and/or polylactic acid with cellulose acetate and/or plasticized cellulose acetate for use in a filter material configured for use in a filter of a smoking article. The bi-component fiber may have a sheath-core construction where one component of the bi-component forms the core, and the other component forms the sheath of each fiber. A filter made in accordance with this design may also include non-biodegradable material.

Disclosed are fibers which contain identification fibers. The identification fibers can contain a plurality of distinct features, or taggants, which vary among the fibers and/or along the length of the identification fibers, tow band, or yarn. The disclosed embodiments also relate to the method for making the fibers. Characterization of the fibers can include identifying distinct features, combinations of distinct features, and number of fibers with various combinations of distinct features and correlating the distinct features to supply chain information. The supply chain information can be used to track the fibers, fiber band, or yarn from manufacturing through intermediaries, conversion to final product, and/or the consumer.

A biodegradable bi-component fiber may include a polyhydroxyalkanoate and/or polylactic acid with cellulose acetate and/or plasticized cellulose acetate for use in a filter material configured for use in a filter of a smoking article. The bi-component fiber may have a sheath-core construction where one component of the bi-component forms the core, and the other component forms the sheath of each fiber. A filter made in accordance with this design may also include non-biodegradable material.

Disclosed are fibers which contain identification fibers. The identification fibers can contain a plurality of distinct features, or taggants, which vary among the fibers and/or along the length of the identification fibers, tow band, or yarn. The disclosed embodiments also relate to the method for making the fibers. Characterization of the fibers can include identifying distinct features, combinations of distinct features, and number of fibers with various combinations of distinct features and correlating the distinct features to supply chain information. The supply chain information can be used to track the fibers, fiber band, or yarn from manufacturing through intermediaries, conversion to final product, and/or the consumer.

Disclosed are fibers which contains identification fibers. The identification fibers can contain a plurality of distinct features, or taggants, which vary among the fibers and/or along the length of the identification fibers of the fibers, a fiber band, or. The disclosed embodiments also relate to the method for making and characterizing the fibers. Characterization of the fibers can include identifying distinct features, combinations of distinct features, and number of fibers with various combinations of distinct features to supply chain information. The supply chain information can be used to track the fibers, fiber band, or yarn from manufacturing through intermediaries, conversion to final product, and/or the consumer.

Disclosed are fibers comprising one or more branded fibers which exhibit surface markings in a repeated pattern along the length of the branded fibers. The branded fibers can be incorporated into yarns or fiber bands to represent supply chain information of the yarns, fiber bands, and/or articles made from the yards or fiber bands. In a specific example, branded fibers can be incorporated into an acetate tow band The branded fibers can be recovered from a cigarette filter, the repeated pattern decoded, and supply chain information associated with the acetate tow used to make the cigarette filter, such as manufacturer, customer, ship to location, and even the acetate tow bale, can be obtained.