SPARSE CODING IN THE PRIMATE CORTEX

By Peter Földiák. 2002

How researchers see this paper

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

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…& Redlich, 1992; Baldi & Hornik, 1989; Barlow, Kaushal, & Mitchison, 1989; Barrow, 1987; Deco & Parra, 1997; Field, 1987; Földiák, 1990; Földiák & Young, 1995; Grossberg, 1976a, 1976b; Hebb, 1949; Kohonen, 1972, 1982, 1988; Kosko, 1990; Martinetz, Ritter, & Schulten, 1990; Miller, 1994; Mozer,…”
Re-evaluating circuit mechanisms underlying pattern separation (2019, positive): “As Marr-Albus theory was extended to other brain regions, such ‘ultra-sparse’ population coding formed the core of our current understanding of pattern separation, associative learning, and memory storage (Marr, 1971; Kanerva, 1988; Tsodyks et al., 1988; Rolls and Treves, 1990; Tyrrell and Willshaw,”
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models (2021, background): “, 1990] and has driven fundamental progress in other fields such as statistics [Tibshirani, 1996], neuroscience [Foldiak, 2003], and signal processing [Candes et al.”
Encoding of mixtures in a simple olfactory system. (2013, unknown): “This is economical for encoding, but bad for storage (Field, 1994; Foldiak, 2003) because (among others) different memories would nearly always share synapses and interfere with one another.”
Sparse coding with memristor networks. (2017, methodology): “…ﬁ cient digital approach shows that an integrated memristor system based on devices similar to the prototype system can already offer signi ﬁ cant energy advantages when performing data-intensive tasks such as real-time video analysis (Supplementary Figs 22 – 25 and Supplementary Tables 1 and 2).”
Discovering hierarchical speech features using convolutional non-negative matrix factorization (2003, background): “Sparse codes combine advantages of local and dense codes while avoiding most of their drawbacks [16].”
Saliency, attention, and visual search: an information theoretic approach. (2009, unknown): “…evidence in favor of sparse coding strategies in the cortex, with sparse coding an important and ubiquitous property of cortical coding (Foldiak & Young, 1995) and having the implication that the response of cells coding for content at a particular spatial location are relatively…”
Sparse coding of sensory inputs. (2004, background): “If the idea of sparse overcomplete codes is carried to an extreme, however, it inevitably leads to a ‘grandmother cell’ type representation, in which a single unique neuron is active for each and every event occurring in the environment [33].”
On the biological plausibility of grandmother cells: implications for neural network theories in psychology and neuroscience. (2009, background): “, Földiák, P., & Perrett, D. I. (2001). The speed of”