---

%PDF-1.3 1 0 obj << /Kids [ 4 0 R 5 0 R 6 0 R 7 0 R 8 0 R 9 0 R 10 0 R 11 0 R 12 0 R ] /Type /Pages /Count 9 >> endobj 2 0 obj << /Subject (Neural Information Processing Systems http\072\057\057nips\056cc\057) /Publisher (Curran Associates\054 Inc\056) /Language (en\055US) /Created (2014) /EventType (Poster) /Description-Abstract (We propose a new framework for estimating generative models via adversarial nets\054 in which we simultaneously train two models\072 a generative model G that captures the data distribution\054 and a discriminative model D that estimates the probability that a sample came from the training data rather than G\056 The training procedure for G is to maximize the probability of D making a mistake\056 This framework corresponds to a minimax two\055player game\056 In the space of arbitrary functions G and D\054 a unique solution exists\054 with G recovering the training data distribution and D equal to 1\0572 everywhere\056 In the case where G and D are defined by multilayer perceptrons\054 the entire system can be trained with backpropagation\056 There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples\056 Experiments demonstrate the potential of the framework through qualitative and quantitatively evaluation of the generated samples\056) /Producer (PyPDF2) /Title (Generative Adversarial Nets) /Date (2014) /ModDate (D\07220141202174320\05508\04700\047) /Published (2014) /Type (Conference Proceedings) /firstpage (2672) /Book (Advances in Neural Information Processing Systems 27) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (Z\056 Ghahramani and M\056 Welling and C\056 Cortes and N\056D\056 Lawrence and K\056Q\056 Weinberger) /Author (Ian Goodfellow\054 Jean Pouget\055Abadie\054 Mehdi Mirza\054 Bing Xu\054 David Warde\055Farley\054 Sherjil Ozair\054 Aaron Courville\054 Yoshua Bengio) /lastpage (2680) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Type /Page /Resources 14 0 R /MediaBox [ 0 0 612 792 ] >> endobj 5 0 obj << /Contents 48 0 R /Parent 1 0 R /Type /Page /Resources 49 0 R /MediaBox [ 0 0 612 792 ] >> endobj 6 0 obj << /Contents 78 0 R /Parent 1 0 R /Type /Page /Resources 79 0 R /MediaBox [ 0 0 612 792 ] >> endobj 7 0 obj << /Contents 84 0 R /Parent 1 0 R /Resources 85 0 R /Group 133 0 R /MediaBox [ 0 0 612 792 ] /Type /Page >> endobj 8 0 obj << /Contents 167 0 R /Parent 1 0 R /Type /Page /Resources 168 0 R /MediaBox [ 0 0 612 792 ] >> endobj 9 0 obj << /Contents 169 0 R /Parent 1 0 R /Type /Page /Resources 170 0 R /MediaBox [ 0 0 612 792 ] >> endobj 10 0 obj << /Contents 175 0 R /Parent 1 0 R /Type /Page /Resources 176 0 R /MediaBox [ 0 0 612 792 ] >> endobj 11 0 obj << /Contents 183 0 R /Parent 1 0 R /Type /Page /Resources 184 0 R /MediaBox [ 0 0 612 792 ] >> endobj 12 0 obj << /Contents 185 0 R /Parent 1 0 R /Type /Page /Resources 186 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3412 /Filter /FlateDecode >> stream xڕZY��6~����RU#�x�ͱ�]��d=�����HXS���3��>��p�ه\M����k@���B���-�|!�=�0�<�Xy��v�<�T�g��i��ů/~�}��m"=�Rđw{��Pq{I�a.���������و�����f+��Uq���5w�C�����?�^��@��ΧϡW��{/r`�Ȏ�b����wy�'2A��$^"� Sf�]����72���ܶ՝����Gv^��K�

---