|
|
American Statistical Association
|
The aim of this talk is to discuss deep learning as a statistical method in data science and its philosophical implications. Statistics is a mode of viewing the world. We think that reality is composed of patterns, which can become clear through statistical and data science methods. In statistical data science methods, hypotheses are formulated in terms of probability distributions over possible datasets of empirical facts. In the application of statistical methods, learning is increasingly becoming a component. Statistical learning is applying automated learning algorithms to identify the features of systems and recognize patterns in very-large datasets.
Deep learning is an advanced statistical method that has come into use in recent years. In deep learning, algorithms learn from and make predictions about data, particularly by modeling high-level abstractions in datasets and assigning probability-weighting to nodes as they move through the system modeling. An important challenge in deep learning is that these methods seem to work, but we do not have a good explanation for why, which prevents a wider application to problems beyond the domains of their current success in image recognition (with convolutional nets) and text/speech recognition (with recurrent nets). This talk looks at what happens in deep learning, where there are multiple layers of increasingly abstract representation and non-linear operation used by algorithms to determine an answer. Deep learning is essentially a complexity optimization problem, where some concepts that may explain how deep learning systems operate include backpropagation, supervised-unsupervised learning, attractors, non-convexity, saddle-point local minima-maxima, and energy-based models (probabilities sum to > 1).
The philosophy of statistical deep learning involves the meaning, justification, use, and interpretation of these methods to arrive at empirical scientific knowledge. How are we to understand and trust these methods as an explanatory mechanism for patterns in datasets? Since statistical data science methods are crucial to any field of scientific inquiry as an interpretation mechanism for empirical data, a better understanding of the theory underlying current topics such as deep learning may help to improve our overall understanding.
Melanie Swan is a Philosopher and Economic Theorist at the New School for Social Research in New York, NY. She is the founder of several startups including the Institute for Blockchain Studies, DIYgenomics, GroupPurchase, and the MS Futures Group. Ms. Swan's educational background includes an MBA in Finance and Accounting from the Wharton School of the University of Pennsylvania, an MA in Contemporary Continental Philosophy from Kingston University London and Université Paris 8, and a BA in French and Economics from Georgetown University. She is a faculty member at Singularity University and the University of the Commons, an Affiliate Scholar at the Institute for Ethics and Emerging Technologies, and a contributor to the Edge's Annual Essay Question.
Arel, Itamar, Rose, Derek C., and Karnowski, Thomas P. (2010). Deep Machine Learning: A New Frontier in Artificial Intelligence Research. IEEE Computational Intelligence Magazine. 5(4). Pp. 13-18.
Cassirer, Ernst. (2017, 1923). Substance and Function, and Einstein's Theory of Relativity. London UK: Forgotten Books. (probability, explanation)
Goodfellow, Ian, Bengio, Yoshua, and Courville, Aaron. (2016). Deep Learning (Adaptive Computation and Machine Learning series). Cambridge MA: MIT Press.
http://www.deeplearningbook.org/slides/01_intro.pdf
Karpathy, Andrej. (2015). The Unreasonable Effectiveness of Recurrent Neural Networks.
LeCun, Yann, Bengio, Yoshua, and Hinton, Geoffrey. (2015). Deep Learning. Nature. 521. Pp. 436-444).
Metz, Cade. (2015). Wolfram's Image Recognition Reflects a Big Shift in AI. WIRED.
Schmidhuber, Juergen. (2015). Deep Learning in Neural Networks: An Overview. Neural Networks. 61. Pp. 85-117.
Swan, Melanie. (2015). Philosophy of Big Data: Expanding the Human-Data Relation with Big Data Science Services. IEEE BigDataService, Redwood City CA, Mar 31-Apr 2, 2015. http://www.melanieswan.com/documents/Philosophy_of_Big_Data_SWAN.pdf
