%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 13 0 R 14 0 R ] /Type /Pages /Count 11 >> 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 (2017) /EventType (Poster) /Description-Abstract (A capsule is a group of neurons whose activity vector represents the instantiation parameters of a specific type of entity such as an object or object part\056 We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters\056 Active capsules at one level make predictions\054 via transformation matrices\054 for the instantiation parameters of higher\055level capsules\056 When multiple predictions agree\054 a higher level capsule becomes active\056 We show that a discrimininatively trained\054 multi\055layer capsule system achieves state\055of\055the\055art performance on MNIST and is considerably better than a convolutional net at recognizing highly overlapping digits\056 To achieve these results we use an iterative routing\055by\055agreement mechanism\072 A lower\055level capsule prefers to send its output to higher level capsules whose activity vectors have a big scalar product with the prediction coming from the lower\055level capsule\056) /Producer (PyPDF2) /Title (Dynamic Routing Between Capsules) /Date (2017) /ModDate (D\07220180212230326\05508\04700\047) /Published (2017) /Type (Conference Proceedings) /firstpage (3856) /Book (Advances in Neural Information Processing Systems 30) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (I\056 Guyon and U\056V\056 Luxburg and S\056 Bengio and H\056 Wallach and R\056 Fergus and S\056 Vishwanathan and R\056 Garnett) /Author (Sara Sabour\054 Nicholas Frosst\054 Geoffrey E\056 Hinton) /lastpage (3866) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 15 0 R /Parent 1 0 R /Resources 16 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 31 0 R 32 0 R 33 0 R 34 0 R 35 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 36 0 R /Parent 1 0 R /Resources 37 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 70 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 71 0 R /Parent 1 0 R /Resources 72 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 81 0 R 82 0 R 83 0 R 84 0 R 85 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 86 0 R /Parent 1 0 R /Resources 87 0 R /Group 92 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 93 0 R 94 0 R 95 0 R 96 0 R 97 0 R 98 0 R 99 0 R 100 0 R 101 0 R 102 0 R 103 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 104 0 R /Parent 1 0 R /Resources 105 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 112 0 R 113 0 R 114 0 R 115 0 R 116 0 R 117 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 118 0 R /Parent 1 0 R /Resources 119 0 R /Group 92 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 136 0 R 137 0 R 138 0 R 139 0 R 140 0 R 141 0 R 142 0 R 143 0 R 144 0 R 145 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 146 0 R /Parent 1 0 R /Resources 147 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 164 0 R 165 0 R 166 0 R 167 0 R 168 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 169 0 R /Parent 1 0 R /Resources 170 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 171 0 R 172 0 R 173 0 R 174 0 R 175 0 R 176 0 R 177 0 R 178 0 R 179 0 R 180 0 R 181 0 R 182 0 R 183 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 184 0 R /Parent 1 0 R /Resources 185 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 186 0 R 187 0 R 188 0 R 189 0 R 190 0 R 191 0 R 192 0 R 193 0 R 194 0 R 195 0 R 196 0 R 197 0 R 198 0 R 199 0 R ] /Type /Page >> endobj 13 0 obj << /Contents 200 0 R /Parent 1 0 R /Type /Page /Resources 201 0 R /MediaBox [ 0 0 612 792 ] >> endobj 14 0 obj << /Contents 202 0 R /Parent 1 0 R /Resources 203 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 207 0 R 208 0 R 209 0 R 210 0 R ] /Type /Page >> endobj 15 0 obj << /Length 3038 /Filter /FlateDecode >> stream xڅYKϯZ1 HSήdx$x)Bcr*= t8"w YtX8GQʤ2jv0(MRF~/ˋDpEOhieR4zG_VH`QwG|g:|]_U旧=ea%V,jǀ*r[c ˣ\ Ǻzg~d㏺9p}ela lmE|V+yMg7E O"+-XEd98ORZ)YlzđvZUvzp"l7ÆHߎ1g\Z.*)%_`*f 0u44;_0&a4)<*dXl *n؛MsNMZ|2$+|pf4={uՠ6'h7u7zԆk!Uh]|pQ1`^B`SsEKջ_A j53+ULM+8i4ɥDiP)[Z&W+ pS?kzEқ]-N[fVb ,f9ʓ~5C"+w8OudM QvJ.^NHi Y%ʦU9mhg'{ 'eZ34f S{X7)n8نIhQ>k^Gx9bT'}<~#XRf۔Y/:ɲv<ȷ@<R=dEVvrm{{ҫ