Apoha theory could perhaps be understood as a part of the Buddhist program of emancipating people from the clutches of attachment. Diṅnāga and thereafter Dharmakīrti, when they developed their epistemology of perception, inference, and language, pointed out that through perception we are associated with unique particulars, which are momentary. We try to give an enduring status to them through thought and language by constructing universals. Thus, thought and language amount to false constructions, and they also mark our attachment to the (...) world. Hence, the realization that helps in preventing such an attachment would imply that inference and language do not really ‘refer to’ or ‘associate themselves with’ what is .. (shrink)
Though I loved Sanskrit, I had a skeptical and heretical attitude towards many beliefs cherished in Sanskrit knowledge systems. I found philosophy to be the right platform to pursue noble ideals without compromising my skeptical and heretical approach. While criticizing Śaṅkara’s Advaita-Vedānta perspective, I tried to present a reconstruction of the Lokāyata perspective, which is traditionally identified with Indian materialism, by making it more intelligible and relevant. The orthodox-heterodox division of Indian Philosophy was also important for me for its moral-social (...) implications. Hence, I was interested in Jainism and Buddhism. My research interests in these schools covered their ethics, epistemology, and logic. My studies in Buddhism led me to take seriously the impact of Buddhism on Indian culture, and also the rational and secular reconstruction of Buddhism rendered by the thinkers like Satyanarayan Goenka, Buddhadasa Bhikkhu, and B. R. Ambedkar. One of the driving forces in my intellectual journey has been my view that if the Indian social order is to be rid of the caste system and made more rational and moral as well as less superstitious and unjust, the centrality of Brahmanical schools has to be replaced by that of non-Brahmanical schools. (shrink)
Philosophy in Indian tradition as a purely secular and rational exercise can be located in the Lokayata/Carvaka school of Indian philosophy. Due to the lack of substantial literary sources, scholars did not try to explore Lokayata philosophically. The present work is the first attempt to explore the philosophical energies inherent in the scattered Carvaka literature through critical and analytical discussions firmly grounded in textual evidences.
The greatest strength of Pradeep P. Gokhale's Lokāyata/Cārvāka: A Philosophical Inquiry is its much-needed enrichment of the vocabulary for the study of the Indian Lokāyata/Cārvāka school. For too long this school has been studied in the rather limited terms of its opponents in texts such as Mādhava's Sarvadarśanasaṃgraha, which identify a single Cārvāka position advocating extreme empiricism in epistemology, materialism in metaphysics, and hedonism and irreligiousness in ethics. Gokhale establishes frameworks for understanding the diversity of epistemological, metaphysical, and (...) axiological positions of Cārvāka philosophers that ought to be considered by anyone writing on the school in the future.Chapter 1... (shrink)
This paper reviews four significant advances on the feedforward architecture that has dominated discussions of connectionism. The first involves introducing modularity into networks by employing procedures whereby different networks learn to perform different components of a task, and a Gating Network determines which network is best equiped to respond to a given input. The second consists in the use of recurrent inputs whereby information from a previous cycle of processing is made available on later cycles. The third development involves developing (...) compressed representations of strings in which there is no longer an explicit encoding of the components but where information about the structure of the original string can be recovered and so is present functionally. The final advance entails using connectionist learning procedures not just to change weights in networks but to change the patterns used as inputs to the network. These advances significantly increase the usefulness of connectionist networks for modeling human cognitive performance by, among other things, providing tools for explaining the productivity and systematicity of some mental activities, and developing representations that are sensitive to the content they are to represent. (shrink)
There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of classical symbolic theories. This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations. An experiment is performed using Pollack’s Recursive (...) Auto-Associative Memory. RAAM is used to construct distributed representations of syntactically structured sentences. A feed-forward network is then trained to operate directly on these representations, modeling syn- tactic transformations of the represented sentences. Successful training and generalization is obtained, demonstrating that the implicit structure present in these representations can be used for a kind of structure-sensitive processing unique to the connectionist domain. (shrink)