%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 (2016) /EventType (Poster) /Description-Abstract (How do people learn about complex functional structure\077 Taking inspiration from other areas of cognitive science\054 we propose that this is accomplished by harnessing compositionality\072 complex structure is decomposed into simpler building blocks\056 We formalize this idea within the framework of Bayesian regression using a grammar over Gaussian process kernels\056 We show that participants prefer compositional over non\055compositional function extrapolations\054 that samples from the human prior over functions are best described by a compositional model\054 and that people perceive compositional functions as more predictable than their non\055compositional but otherwise similar counterparts\056 We argue that the compositional nature of intuitive functions is consistent with broad principles of human cognition\056) /Producer (PyPDF2) /Title (Probing the Compositionality of Intuitive Functions) /Date (2016) /ModDate (D\07220161119112107\05508\04700\047) /Published (2016) /Type (Conference Proceedings) /firstpage (3729) /Book (Advances In Neural Information Processing Systems 29) /Description (Paper accepted and presented at the Neural Information Processing Systems Conference \050http\072\057\057nips\056cc\057\051) /Editors (D\056D\056 Lee and U\056V\056 Luxburg and I\056 Guyon and R\056 Garnett) /Author (Eric Schulz\054 Josh Tenenbaum\054 David K\056 Duvenaud\054 Maarten Speekenbrink\054 Samuel J\056 Gershman) /lastpage (3737) >> endobj 3 0 obj << /Type /Catalog /Pages 1 0 R >> endobj 4 0 obj << /Contents 13 0 R /Parent 1 0 R /Resources 14 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 24 0 R 25 0 R 26 0 R 27 0 R 28 0 R 29 0 R 30 0 R 31 0 R 32 0 R ] /Type /Page >> endobj 5 0 obj << /Contents 33 0 R /Parent 1 0 R /Resources 34 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 71 0 R 72 0 R 73 0 R 74 0 R 75 0 R 76 0 R 77 0 R 78 0 R 79 0 R 80 0 R ] /Type /Page >> endobj 6 0 obj << /Contents 81 0 R /Parent 1 0 R /Resources 82 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 105 0 R 106 0 R 107 0 R 108 0 R 109 0 R 110 0 R 111 0 R ] /Type /Page >> endobj 7 0 obj << /Contents 112 0 R /Parent 1 0 R /Resources 113 0 R /Group 170 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 171 0 R 172 0 R 173 0 R ] /Type /Page >> endobj 8 0 obj << /Contents 174 0 R /Parent 1 0 R /Resources 175 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 183 0 R 184 0 R ] /Type /Page >> endobj 9 0 obj << /Contents 185 0 R /Parent 1 0 R /Resources 186 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 205 0 R 206 0 R 207 0 R 208 0 R 209 0 R ] /Type /Page >> endobj 10 0 obj << /Contents 210 0 R /Parent 1 0 R /Resources 211 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 234 0 R 235 0 R 236 0 R 237 0 R 238 0 R 239 0 R ] /Type /Page >> endobj 11 0 obj << /Contents 240 0 R /Parent 1 0 R /Resources 241 0 R /MediaBox [ 0 0 612 792 ] /Annots [ 258 0 R 259 0 R 260 0 R 261 0 R 262 0 R 263 0 R 264 0 R 265 0 R 266 0 R ] /Type /Page >> endobj 12 0 obj << /Contents 267 0 R /Parent 1 0 R /Type /Page /Resources 268 0 R /MediaBox [ 0 0 612 792 ] >> endobj 13 0 obj << /Length 3124 /Filter /FlateDecode >> stream xZY6~_fsIv%)olDA<)xӍnP$%Re >>&o*J*sdUopQJ"OVYns柿$Jf"[I(Wi"QC]