Online research in philosophy

The neural blackboard architecture is a localist structured connectionist model that employs a novel connection matrix to implement dynamic bindings without requiring propagation of temporal synchrony. Here I note the apparent need for many distinct matrices and the effect this might have for scale-up to semantic processing. I also comment on the authors' initial foray into the symbol grounding problem.

Neural algorithms are conserved during evolution. Neurons with different shapes and using different molecular mechanisms can perform the same computation. However, evolutionary conservation of neural algorithms is not sufficient for claiming the realization of an algorithm for a specific computational problem. A plausible scheme for ontogenetic emergence of the structure of the algorithm must also be provided.

Roughly speaking, computationalism says that cognition is computation, or that cognitive phenomena are explained by the agent‘s computations. The cognitive processes and behavior of agents are the explanandum. The computations performed by the agents‘ cognitive systems are the proposed explanans. Since the cognitive systems of biological organisms are their nervous 1 systems (plus or minus a bit), we may say that according to computationalism, the cognitive processes and behavior of organisms are explained by neural computations. Some people might prefer to say that cognitive systems are ―realized‖ by nervous systems, and thus that—according to computationalism—cognitive computations are ―realized‖ by neural processes. In this paper, nothing hinges on the nature of the relation between cognitive systems and nervous systems, or between computations and neural processes. For present purposes, if a neural process realizes a computation, then that neural process is a computation. Thus, I will couch much of my discussion in terms of nervous systems and neural computation.1 Before proceeding, we should dispense with a possible red herring. Contrary to a common assumption, computationalism does not stand in opposition to connectionism. Connectionism, in the most general and common sense of the term, is the claim that cognitive phenomena are explained (at some level and at least in part) by the processes of neural networks. This is a truism, supported by most neuroscientific evidence. Everybody ought to be a connectionist in this general sense. The relevant question is, are neural processes computations? More precisely, are the neural processes to be found in the nervous systems of organisms computations? Computationalists say ―yes‖, anti-computationalists say ―no‖. This paper investigates whether any of the arguments on offer against computationalism have a chance at knocking it off.2 Ever since Warren McCulloch and Walter Pitts (1943) first proposed it, computationalism has been subjected to a wide range of objections..

``Neural computing'' is a research field based on perceiving the human brain as an information system. This system reads its input continuously via the different senses, encodes data into various biophysical variables such as membrane potentials or neural firing rates, stores information using different kinds of memories (e.g., short-term memory, long-term memory, associative memory), performs some operations called ``computation'', and outputs onto various channels, including motor control commands, decisions, thoughts, and feelings. We show a natural model of neural computing that gives rise to hyper-computation. Rigorous mathematical analysis is applied, explicating our model's exact computational power and how it changes with the change of parameters. Our analog neural network allows for supra-Turing power while keeping track of computational constraints, and thus embeds a possible answer to the superiority of the biological intelligence within the framework of classical computer science. We further propose it as standard in the field of analog computation, functioning in a role similar to that of the universal Turing machine in digital computation. In particular an analog of the Church-Turing thesis of digital computation is stated where the neural network takes place of the Turing machine.

If connectionism is to be an adequate theory of mind, we must have a theory of representation for neural networks that allows for individual differences in weighting and architecture while preserving sameness, or at least similarity, of content. In this paper we propose a procedure for measuring sameness of content of neural representations. We argue that the correct way to compare neural representations is through analysis of the distances between neural activations, and we present a method for doing so. We then use the technique to demonstrate empirically that different artificial neural networks trained by backpropagation on the same categorization task, even with different representational encodings of the input patterns and different numbers of hidden units, reach states in which representations at the hidden units are similar. We discuss how this work provides a rebuttal to Fodor and Lepore's critique of Paul Churchland's state space semantics.

Human cognition is unique in the way in which it relies on combinatorial (or compositional) structures. Language provides ample evidence for the existence of combinatorial structures, but they can also be found in visual cognition. To understand the neural basis of human cognition, it is therefore essential to understand how combinatorial structures can be instantiated in neural terms. In his recent book on the foundations of language, Jackendoff described four fundamental problems for a neural instantiation of combinatorial structures: the massiveness of the binding problem, the problem of 2, the problem of variables, and the transformation of combinatorial structures from working memory to long-term memory. This paper aims to show that these problems can be solved by means of neural “blackboard” architectures. For this purpose, a neural blackboard architecture for sentence structure is presented. In this architecture, neural structures that encode for words are temporarily bound in a manner that preserves the structure of the sentence. It is shown that the architecture solves the four problems presented by Jackendoff. The ability of the architecture to instantiate sentence structures is illustrated with examples of sentence complexity observed in human language performance. Similarities exist between the architecture for sentence structure and blackboard architectures for combinatorial structures in visual cognition, derived from the structure of the visual cortex. These architectures are briefly discussed, together with an example of a combinatorial structure in which the blackboard architectures for language and vision are combined. In this way, the architecture for language is grounded in perception. Perspectives and potential developments of the architectures are discussed. Key Words: binding; blackboard architectures; combinatorial structure; compositionality; language; dynamic system; neurocognition; sentence complexity; sentence structure; working memory; variables; vision.

We review the pros and cons of analog and digital computation. We propose that computation that is most efficient in its use of resources is neither analog computation nor digital computation but, rather, a mixture of the two forms. For maximum efficiency, the information and information-processing resources of the hybrid form must be distributed over many wires, with an optimal signal-to-noise ratio per wire. Our results suggest that it is likely that the brain computes in a hybrid fashion and that an underappreciated and important reason for the efficiency of the human brain, which consumes only 12 W, is the hybrid and distributed nature of its architecture.

The target article does not provide insight into how the proposed neural blackboard architecture can be mapped to known neural structures in the brain. There are theories suggesting that the thalamus may be a good candidate. However, the experimental evidence suggests that the cortex may be involved (if in fact the blackboard is implemented in the brain). Issues arising from such a mapping will be discussed.

I address whether neural networks perform computations in the sense of computability theory and computer science. I explicate and defend
the following theses. (1) Many neural networks compute—they perform computations. (2) Some neural networks compute in a classical way.
Ordinary digital computers, which are very large networks of logic gates, belong in this class of neural networks. (3) Other neural networks
compute in a non-classical way. (4) Yet other neural networks do not perform computations. Brains may well fall into this last class.