Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning

<div>The convergence measure <span class="nowrap"><svg height="12.1175pt" id="M168" style="vertical-align:-3.27283pt" version="1.1" viewbox="-0.0498162 -8.84467 32.0138 12.1175" width="32.0138pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M1048 672C1036 675 1028 674 1020 674C822 646 666 318 554 134C521 81 495 39 468 39C457 39 455 46 455 57C455 79 469 109 472 118C520 227 653 461 794 660L779 672C768 675 766 674 762 674C654 674 544 586 344 250C241 78 187 15 119 15C104 15 91 21 88 36H91C96 33 101 32 106 32C133 32 149 53 149 76C149 103 128 128 97 128C65 128 38 102 38 63C38 20 71 -15 118 -15C235 -15 307 132 473 397C542 508 638 615 712 644L713 643C646 565 574 455 521 373C460 281 378 144 378 66C378 23 399 -4 434 -4C518 -4 559 76 647 231C792 488 891 603 977 635L978 633C779 366 670 179 670 70C670 18 708 -12 756 -12C819 -12 883 42 959 134L940 150C868 66 810 18 770 18C751 18 737 28 737 53C737 111 865 359 1056 659L1048 672Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,13.936,3.132)"><path d="M390 111C344 68 312 56 269 56C212 56 118 102 118 241C118 346 175 401 241 401C277 401 312 388 342 360C350 352 355 349 361 349C372 349 394 371 394 392C394 403 391 411 378 422C362 436 329 449 288 449H287C250 449 190 432 138 392C71 341 37 274 37 197C37 90 112 -12 238 -12C297 -12 363 32 407 90L390 111Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,17.785,3.132)"><path d="M257 449C165 449 37 374 37 209C37 98 119 -12 256 -12C355 -12 473 65 473 226C473 349 381 449 257 449ZM244 416C333 416 380 320 380 204C380 67 329 21 267 21C184 21 130 115 130 241C130 354 184 416 244 416Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,22.317,3.132)"><path d="M524 0V26C466 32 460 36 460 104V297C460 393 411 449 331 449C302 449 276 437 248 419C223 402 201 387 181 372V451C137 432 90 420 42 411V388C96 378 102 374 102 310V104C102 38 97 33 29 26V0H246V26C187 32 181 36 181 104V339C211 365 250 390 290 390C357 390 381 345 381 276V109C381 40 374 32 315 26V0H524Z"></path></g><g transform="matrix(.0091,0,0,-0.0091,27.084,3.132)"><path d="M478 437H300V411C357 404 363 393 347 345C325 280 293 190 258 107C229 178 188 284 163 354C147 397 149 405 203 411V437H-2V411C52 403 59 396 82 339C130 222 176 109 220 -11H248C304 138 356 261 390 336C417 395 425 404 478 411V437Z"></path></g></svg>.</span></div>

Computational Intelligence and Neuroscience

fig12

Figure 12

Figure 12: Information-Based Boundary Equilibrium Generative Adversarial Networks with Interpretable Representation Learning 