%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 (2013) /EventType (Poster) /Description-Abstract (Local competition among neighboring neurons is common in biological neural networks \050NNs\051\056 We apply the concept to gradient\055based\054 backprop\055trained artificial multilayer NNs\056 NNs with competing linear units tend to outperform those with non\055competing nonlinear units\054 and avoid catastrophic forgetting when training sets change over time\056) /Producer (PyPDF2) /Title (Compete to Compute) /Date (2013) /ModDate (D\07220171115173451\05508\04700\047) /Published (2013) /Type (Conference Proceedings) /firstpage (2310) /Book (Advances in Neural Information Processing Systems 26) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (C\056J\056C\056 Burges and L\056 Bottou and M\056 Welling and Z\056 Ghahramani and K\056Q\056 Weinberger) /Author (Rupesh K\056 Srivastava\054 Jonathan Masci\054 Sohrob Kazerounian\054 Faustino Gomez\054 J\374rgen Schmidhuber) /lastpage (2318) >> 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 36 0 R /Parent 1 0 R /Type /Page /Resources 37 0 R /MediaBox [ 0 0 612 792 ] >> endobj 6 0 obj << /Contents 66 0 R /Parent 1 0 R /Type /Page /Resources 67 0 R /MediaBox [ 0 0 612 792 ] >> endobj 7 0 obj << /Contents 81 0 R /Parent 1 0 R /Type /Page /Resources 82 0 R /MediaBox [ 0 0 612 792 ] >> endobj 8 0 obj << /Contents 105 0 R /Parent 1 0 R /Type /Page /Resources 106 0 R /MediaBox [ 0 0 612 792 ] >> endobj 9 0 obj << /Contents 107 0 R /Parent 1 0 R /Type /Page /Resources 108 0 R /MediaBox [ 0 0 612 792 ] >> endobj 10 0 obj << /Contents 109 0 R /Parent 1 0 R /Type /Page /Resources 110 0 R /MediaBox [ 0 0 612 792 ] >> endobj 11 0 obj << /Contents 111 0 R /Parent 1 0 R /Type /Page /Resources 112 0 R /MediaBox [ 0 0 612 792 ] >> endobj 12 0 obj << /Contents 141 0 R /Parent 1 0 R /Type /Page /Resources 142 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 2924 /Filter /FlateDecode >> stream x}ɖܶ>_#6IpEN,?)dχhӍ$:\4 e(_@X(^(8Q]t3.1 ]