Robust logics

By Leslie G. Valiant. 1999

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

Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning (2019, background): “Speciﬁcally, these challenges are: (1) dependency on large datasets required for bottom-up, data-dependent ML algorithms (Valiant 2000; De Palma, Kiani, and Lloyd 2019), (2) bias in the dataset , enabling the model to emphpoten-tially cause social discrimination and unfair treatment, (3)…”
On the Robustness of Information-Theoretic Privacy Measures and Mechanisms (2018, background): “The study of robustness has appeared in many different areas, such as optimization [51], statistics [52], artificial intelligence [53], and machine learning [54].”
AI Reasoning Systems: PAC and Applied Methods (2018, methodology): “ascertain what patterns are actually learned by the algorithm. Table 1: Authors cited in this review who have identiﬁed these 6 issues. Marcus [15] Bottou [2] Garnelo [7] Evans [6] Zhang [23] Valiant [20] Needs too much data X X X X Can’t transfer-learn X X X Can’t encode hierarchy X X X Can’t openl”
Evolvability (2006, unknown): “Robust logic [Valiant 2000] is a mathematical framework based on learning that aims to encompass cognitive tasks beyond learning, particularly reasoning.”
Knowledge Infusion (2006, methodology): “The treatment in (Valiant, 2000b) can be viewed as an extension in the following four directions: preconditions are allowed for each rule, the distribution D need not be symmetric, bindings need not be one-to-one, and universal quantifiers are allowed in addition to existential quantifiers.”
Many-Layered Learning (2002, background): “It will be useful to explore further how variable binding mechanisms can be modeled in networks of simple computational devices (Valiant, 2000a; Valiant, 2000b; Khardon, Roth & Valiant, 1999).”