πŸ”₯ Popular | Latest

( ff via @tech @memes) The system, developed by Abel L. Peirson V and E. Meltem Tolunay, uses a pre-trained Inception-v3 network using the long short-term memory model to produce captions that are applicable to a particular picture. Humans then assess the humor of the meme, rewarding the system for true LOLs. The researchers trained the network with β€œ400.000 image, label and caption triplets with 2600 unique image-label pairs” including funny memes generated by actual humans. The system then recreates memes in a similar vein. Among the various findings, according to the researchers, "we note that there was a bias in the dataset towards expletive, racist and sexist memes, so yet another possibility for future work would be to address this bias." . Want to make your own memes? πŸ€”πŸ€” Go to the @memes page and click the link in their bio to get the MemesApp!! πŸ”₯ . tech computers memes: Stanford researchers have developed a computer system that can generate its own memes ( ff via @tech @memes) The system, developed by Abel L. Peirson V and E. Meltem Tolunay, uses a pre-trained Inception-v3 network using the long short-term memory model to produce captions that are applicable to a particular picture. Humans then assess the humor of the meme, rewarding the system for true LOLs. The researchers trained the network with β€œ400.000 image, label and caption triplets with 2600 unique image-label pairs” including funny memes generated by actual humans. The system then recreates memes in a similar vein. Among the various findings, according to the researchers, "we note that there was a bias in the dataset towards expletive, racist and sexist memes, so yet another possibility for future work would be to address this bias." . Want to make your own memes? πŸ€”πŸ€” Go to the @memes page and click the link in their bio to get the MemesApp!! πŸ”₯ . tech computers memes

( ff via @tech @memes) The system, developed by Abel L. Peirson V and E. Meltem Tolunay, uses a pre-trained Inception-v3 network using th...

Save