Unsupervised learning of invariant representations

By Fabio Anselmi, Joel Z. Leibo, Lorenzo Rosasco, Jim Mutch, Andrea Tacchetti, Tomaso A. Poggio. 2016

102 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, neutral): “models learned for new objects (or new tasks) (Anselmi et al., 2016; Baxter, 2000; Bottou, 2014; Lopez-Oaz, Bottou, Scholköpf, & Vapnik, 2016; Salakhutdinov, Torralba, & Tenenbaum, 2011; Srivastava & Salakhutdinov, 2013; Torralba, Murphy, & Freeman, 2007; Zeiler & Fergus, 2014).”
Safety Verification of Deep Neural Networks (2016, background): “We justify this choice based on the observation [11,23,24] that deep neural networks are thought to compute progressively more powerful invariants as the depth increases.”
View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation (2016, positive): “Our assumptions about the architecture for invariance conform to i-theory [4, 5] which is a theory of invariant recognition that characterizes and generalizes the convolutional and pooling layers in deep networks.”
Understanding Image Representations by Measuring Their Equivariance and Equivalence (2014, background): “By contrast, our aim is not to propose yet another mechanism to learn invariances (Anselmi et al. 2016; Bruna and Mallat 2013; Huang et al. 2007) or equivariance (Dieleman et al.”
Toward an Integration of Deep Learning and Neuroscience (2016, background): “et associate the object with a speciﬁc name or label. Once such an invariant signature is established, however, it becomes basically trivial to associate the signature with a label for classiﬁcation (Anselmi et al., 2015). Poggio (2015) also suggests speciﬁc means, in the context of I-theory (Anselm”
Building Machines that Learn and Think Like People (2018, unknown): “models learned for new objects (or new tasks) (Anselmi et al., 2016; Baxter, 2000; Bottou, 2014; Lopez-Oaz, Bottou, Scholköpf, & Vapnik, 2016; Salakhutdinov, Torralba, & Tenenbaum, 2011; Srivastava & Salakhutdinov, 2013; Torralba, Murphy, & Freeman, 2007; Zeiler & Fergus, 2014).”
Deep-learning inversion: a next generation seismic velocity-model building method (2019, background): “They are also studied as neuro-physiological models of vision (Anselmi et al., 2016).”
On the Expressive Power of Deep Learning: A Tensor Analysis (2015, unknown): “4 we take this further by showing that the shared HT model is exponentially more expressive than CP model, even if the latter is not constrained by sharing.”
Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy? (2015, background): “showed that image representations invariant to transformations such as translations and scaling can considerably reduce the sample complexity of learning and that a deep architecture with filtering and pooling can learn such invariant representations [20].”
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review (2016, background): “ework on nonlinear width guarantee the “polynomial” bounds are optimal. Both shallow and deep representations may or may not reﬂect invariance to group transformations of the inputs of the function ([44, 21]). Invariance – also called weight sharing – decreases the complexity of the network. Since w”