Abstract
Machine Learning has traditionally focused on narrow artificial intelligence - solutions for specific problems. Despite this, we observe two trends in the state-of-the-art: One, increasing architectural homogeneity in algorithms and models. Two, algorithms having more general application: New techniques often beat many benchmarks simultaneously. We review the changes responsible for these trends and look to computational neuroscience literature to anticipate future progress.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381–395 (1981)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 91–99 (2016)
Luo, H., Fu, J., Glass, J.: Bidirectional backpropagation: towards biologically plausible error signal transmission in neural networks. arXiv preprint arXiv:1702.07097 (2017)
Petro, L.S., Vizioli, L., Muckli, L.: Contributions of cortical feedback to sensory processing in primary visual cortex. Front. Psychol. 5, 1–8 (2014)
Markov, N.T., Vezoli, J., Chameau, P., Falchier, A., Quilodran, R., Huissoud, C., Lamy, C., Misery, P., Giroud, P., Ullman, S., Barone, P., Dehay, C., Knoblauch, K., Kennedy, H.: Anatomy of hierarchy: feedforward and feedback pathways in Macaque visual cortex. J. Comp. Neurol. 522, 225–259 (2014)
Balduzzi, D., Vanchinathan, H., Buhmann, J.: Kickback cuts Backprops red-tape: biologically plausible credit assignment in neural networks. In: 9th AAAI Conference on Artificial Intelligence (2014)
Bengio, Y., Lee, D.H., Bornschein, J., Mesnard, T., Lin, Z.: Towards biologically plausible deep learning. arXiv preprint arXiv:1502.04156v3 (2016)
Balduzzi, D., Frean, M., Leary, L., Lewis, J.P., Ma, K.W.D., McWilliams, B.: The shattered gradients problem: if resnets are the answer, then what is the question? arXiv preprint arXiv:1702.08591 (2017)
Eldan, R., Shamir, O.: The power of depth for feedforward neural networks. In: 29th Annual Conference on Learning Theory, PMLR, vol. 49, pp. 907–940 (2016)
Jaderberg, M., Czarnecki, W.M., Osindero, S., Vinyals, O., Graves, A., Kavukcuoglu, K.: Decoupled neural interfaces using synthetic gradients. arXiv preprint arXiv:1608.05343 (2016)
Graves, A.: Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850 (2013)
Monner, D.D., Reggia, J.A.: Systematically grounding language through vision in a neural network. In: Artificial General Intelligence: 4th International Conference (2011)
Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. In: International Conference on Learning Representations (2017)
Kaelbling, L.P., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)
McClure, S.M., Laibson, D.I., Loewenstein, G., Cohen, J.D.: Separate neural systems value immediate and delayed monetary rewards. Science 306(5695), 503–507 (2004)
Kim, S., Hwang, J., Seo, H., Lee, D.: Valuation of uncertain and delayed rewards in primate prefrontal cortex. Neural Netw. 22(3), 294–304 (2009)
Hwang, J., Kim, S., Lee, D.: Temporal discounting and inter-temporal choice in rhesus monkeys. Front. Behav. Neurosci. 3(9), 1–13 (2009)
Namboodiria, V.M.K., Levyc, J.M., Mihalasd, S., Simse, D.W., Shulerc, M.G.H.: Rationalizing spatial exploration patterns of wild animals and humans through a temporal discounting framework. In: Proceedings of the National Academy of Sciences, vol. 113, no. 31, pp. 8747–8752 (2016)
Ponsen, M., Taylor, M.E., Tuyls, K.: Abstraction and generalization in reinforcement learning: a summary and framework. In: Taylor, M.E., Tuyls, K. (eds.) ALA 2009. LNCS, vol. 5924, pp. 1–32. Springer, Heidelberg (2010). doi:10.1007/978-3-642-11814-2_1
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)
Baddeley, A., Eysenck, M., Anderson, M.: Memory, chap. 3. Psychology Press, New York (2009)
Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401v2 (2014)
Zaremba, W., Sutskever, I.: Reinforcement learning neural turing machines. In: Proceedings of ICLR 2016 (2016)
Marblestone, A., Wayne, G., Kording, K.: Toward an integration of deep learning and neuroscience. Front. Comput. Neurosci. 7, 137 (2016)
Kheradpisheh, S.R., Ghodrati, M., Ganjtabesh, M., Masquelier, T.: Deep networks can resemble human feed-forward vision in invariant object recognition. Nat. Sci. R 6 (2016). Article 32672
Kheradpisheh, S.R., Ghodrati, M., Ganjtabesh, M., Masquelier, T.: Humans and deep networks largely agree on which kinds of variation make object recognition harder. Front. Comput. Neurosci. 10, 92 (2016)
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., Fergus, R.: Intriguing properties of neural networks. In: International Conference on Learning Representations (2014)
Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: International Conference on Learning Representations (2015)
Bengio, Y., Mesnard, T., Fischer, A., Zhang, S., Wu, Y.: STDP as presynaptic activity times rate of change of postsynaptic activity. arXiv preprint arXiv:1509.05936 (2015)
Oja, E.: A simplified neuron model as a principal component analyzer. J. Math. Biol. 15, 267–273 (1982)
Rumelhart, D. E., McClelland, J. L., The PDP research group: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1 and 2. MIT Press, Cambridge (1986)
Makhzani, A., Frey, B.: Winner-take-all autoencoders. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), pp. 2791–2799 (2015)
Butza, M.: Brain Research Reviews 60(2), 287–305 (2009)
Guergiuev, J., Lillicrap, T.P., Richards, B.A.: Towards deep learning with segregated dendrites. arXiv preprint arXiv:1610.00161 (2016)
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Sjstrm, P.J., Rancz, E.A., Roth, A., Husser, M.: Excitability, dendritic, plasticity, synaptic. Physiol. Rev. 88, 769–840 (2008)
Diehl, P., Cook, M.: Unsupervised learning of digit recognition using spike-timing-dependent plasticity. Front. Comput. Neurosci. 9 (2015). Article 99
Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625–660 (2010)
Erhan, D., Manzagol, P.-A., Bengio, Y., Bengio, S., Vincent, P.: The difficulty of training deep architectures and the effect of unsupervised pre-training. In: International Conference on Artificial Intelligence and Statistics, vol. 5, pp. 153–160 (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (NIPS) (2012)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML, vol. 1, no. 4 (2015)
Shah, A., Kadam, E., Shah, H., Shinde, S., Shingade, S.: Deep residual networks with exponential linear unit. arXiv preprint arXiv:1604.04112 (2016)
Ditzler, G., Roveri, M., Alippi, C., Polikar, R.: Learning in nonstationary environments: a survey. IEEE Comput. Intell. Mag. 10(4), 12–25 (2015)
Schaul, T., Zhang, S., LeCun, Y.: No more Pesky learning rates. In: Proceedings of 30th International Conference on Machine Learning (ICML) (2013)
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., Hassabis, D., Clopath, C., Kumarana, D., Hadsella, R.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521–3526 (2017)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn, p. 733. Prentice Hall, Englewood Cliffs (2003). ISBN 0-13-080302-2
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Transaction on Pattern Analysis and Machine Intelligence (PAMI), vol. 28, no. 4, pp. 594–611 (2006)
Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. In: Proceedings of Computer Vision and Pattern Recognition (CVPR) (2000)
Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., Lillicrap, T.: One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065v1 (2016)
Lee, S.W., ODoherty, J.P., Shimojo, S.: Neural computations mediating one-shot learning in the human brain. PLoS Biol 13(4), e1002137 (2015)
Silver, D., Yang, Q., Li, L.: Lifelong machine learning systems: beyond learning algorithms. In: Papers from the 2013 AAAI Spring Symposium (2013)
Krahe, R., Gabbiani, F.: Burst firing in sensory systems. Nat. Rev. Neurosci. 5, 13–23 (2004)
Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by VI? Vis. Res. 37(23), 3311–3326 (1997)
Le, Q.V., Ranzato, M.A., Monga, R., Devin, M., Chen, K., Corrado, G.S., Dean, J., Ng, A.Y.: Building high-level features using large scale unsupervised learning. In: Proceedings of the 29th International Conference on Machine Learning (2012)
Coates, A., Ng, A.Y.: The importance of encoding versus training with sparse coding and vector quantization. In: Proceedings of the 28th International Conference on Machine Learning, Bellevue, WA, USA (2011)
Hawkins, J., Ahmad, S.: Why neurons have thousands of synapses, a theory of sequence memory in neocortex. Front. Neural Circ. 10(23), 1–13 (2016)
Kok, P., de Lange, F.P.: Predictive coding in sensory cortex. In: Forstmann, B.U., Wagenmakers, E.-J. (eds.) An Introduction to Model-Based Cognitive Neuroscience. LLC, chap. 11, vol. 221, pp. 221–244. Springer, New York (2015)
Kogo, N., Trengrove, C.: Is predictive coding theory articulated enough to be testable? Front. Comput. Neurosci. 9(111), 357–381 (2015)
Srivastava, N., Greff, K., Schmidhuber, J.: Highway networks. In: Deep Learning Workshop (ICML 2015) (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)
Veit, A., Wilber, M., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. arXiv preprint arXiv:1605.06431 (2016)
Liao, Q., Poggio, T.: Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex. arXiv preprint arXiv:1604.03640 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Rawlinson, D., Kowadlo, G. (2017). Computational Neuroscience Offers Hints for More General Machine Learning. In: Everitt, T., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2017. Lecture Notes in Computer Science(), vol 10414. Springer, Cham. https://doi.org/10.1007/978-3-319-63703-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-63703-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-63702-0
Online ISBN: 978-3-319-63703-7
eBook Packages: Computer ScienceComputer Science (R0)