Downloads & Free Reading Options - Results

Quite a few interesting experiments have been done applying neural networks to natural language tasks. Without detracting from the value of these early investigations, this paper argues that current neural network architectures are too weak to solve anything but toy language problems. Their downfall is the need for 'dynamic inference', in which several pieces of information not previously seen together are dynamically combined to derive the meaning of a novel input. The first half of the paper defines a hierarchy of classes of connectionist models, from categorizers and associative memories to pattern transformers are dynamic inferencers. Some well-known connectionist models that deal with natural language are shown to be either categorizers or pattern transformers. The second half examines in detail a particular natural language problem: prepositional phase attachment. Attaching a PP to an NP changes its meaning, thereby influencing other attachments. So PP attachment requires compositional semantics; and compositionality in non-toy domains requires dynamic inference. Mere pattern transformers cannot learn the PP attachment task without an exponential training set. Connectionist-style computation still has many valuable ideas to offer, so this is not an indictment of connectionisms's potential. Keywords: Knowledge representation; Computer systems; Natural language; Semantics; Artificial intelligence; Connectionist models.

In the mid nineties, the Earth Observing System (EOS) will generate an estimated 10 terabytes of data per day. This enormous amount of data will require the use of sophisticated technologies from real time distributed Artificial Intelligence (AI) and data management. Without regard to the overall problems in distributed AI, efficient models were developed for doing query planning and/or scheduling in intelligent user interfaces that reside in a network environment. Before intelligent query/planning can be done, a model for real time AI planning and/or scheduling must be developed. As Connectionist Models (CM) have shown promise in increasing run times, a connectionist approach to AI planning and/or scheduling is proposed. The solution involves merging a CM rule based system to a general spreading activation model for the generation and selection of plans. The system was implemented in the Rochester Connectionist Simulator and runs on a Sun 3/260.

In the mid nineties, the Earth Observing System (EOS) will generate an estimated 10 terabytes of data per day. This enormous amount of data will require the use of sophisticated technologies from real time distributed Artificial Intelligence (AI) and data management. Without regard to the overall problems in distributed AI, efficient models were developed for doing query planning and/or scheduling in intelligent user interfaces that reside in a network environment. Before intelligent query/planning can be done, a model for real time AI planning and/or scheduling must be developed. As Connectionist Models (CM) have shown promise in increasing run times, a connectionist approach to AI planning and/or scheduling is proposed. The solution involves merging a CM rule based system to a general spreading activation model for the generation and selection of plans. The system was implemented in the Rochester Connectionist Simulator and runs on a Sun 3/260.

In the mid nineties, the Earth Observing System (EOS) will generate an estimated 10 terabytes of data per day. This enormous amount of data will require the use of sophisticated technologies from real time distributed Artificial Intelligence (AI) and data management. Without regard to the overall problems in distributed AI, efficient models were developed for doing query planning and/or scheduling in intelligent user interfaces that reside in a network environment. Before intelligent query/planning can be done, a model for real time AI planning and/or scheduling must be developed. As Connectionist Models (CM) have shown promise in increasing run times, a connectionist approach to AI planning and/or scheduling is proposed. The solution involves merging a CM rule based system to a general spreading activation model for the generation and selection of plans. The system was implemented in the Rochester Connectionist Simulator and runs on a Sun 3/260.

Intelligent systems based on first-order logic on the one hand, and on artificial neural networks (also called connectionist systems) on the other, differ substantially. It would be very desirable to combine the robust neural networking machinery with symbolic knowledge representation and reasoning paradigms like logic programming in such a way that the strengths of either paradigm will be retained. Current state-of-the-art research, however, fails by far to achieve this ultimate goal. As one of the main obstacles to be overcome we perceive the question how symbolic knowledge can be encoded by means of connectionist systems: Satisfactory answers to this will naturally lead the way to knowledge extraction algorithms and to integrated neural-symbolic systems.

Intelligent systems based on first-order logic on the one hand, and on artificial neural networks (also called connectionist systems) on the other, differ substantially. It would be very desirable to combine the robust neural networking machinery with symbolic knowledge representation and reasoning paradigms like logic programming in such a way that the strengths of either paradigm will be retained. Current state-of-the-art research, however, fails by far to achieve this ultimate goal. As one of the main obstacles to be overcome we perceive the question how symbolic knowledge can be encoded by means of connectionist systems: Satisfactory answers to this will naturally lead the way to knowledge extraction algorithms and to integrated neural-symbolic systems.

Intelligent systems based on first-order logic on the one hand, and on artificial neural networks (also called connectionist systems) on the other, differ substantially. It would be very desirable to combine the robust neural networking machinery with symbolic knowledge representation and reasoning paradigms like logic programming in such a way that the strengths of either paradigm will be retained. Current state-of-the-art research, however, fails by far to achieve this ultimate goal. As one of the main obstacles to be overcome we perceive the question how symbolic knowledge can be encoded by means of connectionist systems: Satisfactory answers to this will naturally lead the way to knowledge extraction algorithms and to integrated neural-symbolic systems.

This technical report contains three short articles on different aspects of language and connectionism. Together, the articles illustrate both the promise and the challenges facing the application of connectionist models to central issues in language processing. The first paper, (Reconstructive memory for sentences, by St. John and McClelland) describes a connectionist model in which background knowledge is used to aid recall and fill in missing arguments in sentences. The second, (Parallel distributed processing and role assignment constraints, by J. L. McClelland) discusses the application of connectionist models to the problem of using semantic/pragmatic constraints to processing sentences like 'John ate the cake that his mother baked in the oven' as opposed to 'John ate the cake that his mother baked in the dining room.' The third paper gives a brief overview of the model of past tense learning developed by Rumelhart and McClelland. Keywords: Cognitive psychology, Learning, Language, Connectionism, PDP, PP attachment, Case assignment, Verb tense.

The work of connectionist researchers is examined in order to understand better the implications for modeling second language learning processes. Connectionism is a biologically-oriented framework for understanding complex behavior, and provides a modeling tool (computer simulation) that behaves and learns without rules being explicitly wired into it. Its origins in cognitive science are traced to the 1950s, and its evolution within the field of artificial intelligence is reviewed briefly. It is noted that while there has been some discussion about parallel distributed processing (PDP) and its potential for understanding cognitive processes in the literature of second language acquisition (SLA), there has been little empirical work involving computer simulation of SLA. Several studies have addressed the utility of computer modeling for explaining some discrete SLA phenomena. Some arguments against connectionism are also found. It is concluded that if the more advanced PDP models can overcome some of the current problems and can allow predictions to be made about real second language learners, connectionism can be useful to SLA researchers. (Contains 26 references.) (MSE)

Naturalizing ethics has been a problematic philosophic enterprise. The author attempts a synoptic reconciliation of the sciences with a naturalized conception of morality, beginning with a Quinean refutation of the naturalistic fallacy and the open question argument. We can improve our understanding of the nature of moral theory and its place in moral judgment by treating morality as a natural phenomenon subject to constraints from and ultimately reduced to the cognitive and biological sciences. Treating morality as a mafter of proper biological function, partially fixed by our evolutionary history, and with an emphasis on skillful action in the world (know how), sheds light on the underlying native connectionist architecture of moral cognition. The author discusses practical implications, regarding the nature and form of our collective character development institutions and our methods for moral reasoning, that arise from this approach, reaffirming Deweyian and Aristotelian points about the importance of sociability, friendship, and liberal democratic forms of social organization for human flourishing.

Naturalizing ethics has been a problematic philosophic enterprise. The author attempts a synoptic reconciliation of the sciences with a naturalized conception of morality, beginning with a Quinean refutation of the naturalistic fallacy and the open question argument. We can improve our understanding of the nature of moral theory and its place in moral judgment by treating morality as a natural phenomenon subject to constraints from and ultimately reduced to the cognitive and biological sciences. Treating morality as a mafter of proper biological function, partially fixed by our evolutionary history, and with an emphasis on skillful action in the world (know how), sheds light on the underlying native connectionist architecture of moral cognition. The author discusses practical implications, regarding the nature and form of our collective character development institutions and our methods for moral reasoning, that arise from this approach, reaffirming Deweyian and Aristotelian points about the importance of sociability, friendship, and liberal democratic forms of social organization for human flourishing.

Includes bibliographical references (p. 267-284) and indexes

Includes bibliographical references (p. 267-284) and indexes

Includes bibliographical references (p. 267-284) and indexes

In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To justify this claim, certain critical features that any computational architecture capable of supporting intelligent behavior must possess are identified, and then it is shown that the core features of connectionism correspond exactly to these features. It is also argued that connectionism cannot be viewed merely as an implementation paradigm because its core features influence our conceptions of representation and reasoning in important ways: designing connectionist models for solving complex tasks leads to the identification of constraints on the conceptual structure. The above issues are discussed with reference to two connectionist systems that perform reasoning tasks with extreme efficiency. Keywords: Artificial intelligence.

In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To justify this claim, certain critical features that any computational architecture capable of supporting intelligent behavior must possess are identified, and then it is shown that the core features of connectionism correspond exactly to these features. It is also argued that connectionism cannot be viewed merely as an implementation paradigm because its core features influence our conceptions of representation and reasoning in important ways: designing connectionist models for solving complex tasks leads to the identification of constraints on the conceptual structure. The above issues are discussed with reference to two connectionist systems that perform reasoning tasks with extreme efficiency. Keywords: Artificial intelligence.

In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To justify this claim, certain critical features that any computational architecture capable of supporting intelligent behavior must possess are identified, and then it is shown that the core features of connectionism correspond exactly to these features. It is also argued that connectionism cannot be viewed merely as an implementation paradigm because its core features influence our conceptions of representation and reasoning in important ways: designing connectionist models for solving complex tasks leads to the identification of constraints on the conceptual structure. The above issues are discussed with reference to two connectionist systems that perform reasoning tasks with extreme efficiency. Keywords: Artificial intelligence.

In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To justify this claim, certain critical features that any computational architecture capable of supporting intelligent behavior must possess are identified, and then it is shown that the core features of connectionism correspond exactly to these features. It is also argued that connectionism cannot be viewed merely as an implementation paradigm because its core features influence our conceptions of representation and reasoning in important ways: designing connectionist models for solving complex tasks leads to the identification of constraints on the conceptual structure. The above issues are discussed with reference to two connectionist systems that perform reasoning tasks with extreme efficiency. Keywords: Artificial intelligence.

In this paper it is argued that not only is connectionism relevant to knowledge representation and reasoning, but it also provides an ideal computational architecture for intelligent systems. To justify this claim, certain critical features that any computational architecture capable of supporting intelligent behavior must possess are identified, and then it is shown that the core features of connectionism correspond exactly to these features. It is also argued that connectionism cannot be viewed merely as an implementation paradigm because its core features influence our conceptions of representation and reasoning in important ways: designing connectionist models for solving complex tasks leads to the identification of constraints on the conceptual structure. The above issues are discussed with reference to two connectionist systems that perform reasoning tasks with extreme efficiency. Keywords: Artificial intelligence.

1Mr. Wicker's Window

By Carley Dawson

When twelve-year-old Chris entered Mr. Wicker's shop to inquire about a job for his friend, something about old Mr. Wicker forced him to take the job himself. Chris found himself the pupil of Mr. Wicker, not the old man he first saw, but a powerful man in his forties--a magician. Chris learned how to turn himself into a fish, a bird, a fly, and with a magic rope he learned to make a boat or even an elephant.<br /><br /> Chris had been chosen to sail to China on a mysterious mission. Long before he sailed, Chris met the enemies who would try and stop him--evil Claggett Chew, the dandy Osterbridge Hawsey, the treacherous old beggar Simon Gosler. With a Nubian boy Chris brought to life with magic, he set out on his hazardous voyage.(Summary by Saturday Review of Literature)

2Mr. Wicker's Window (Version 2)

By Carley Dawson

When Christopher Mason walked into Mr. Wicker's antique shop, he had no idea he would soon be embarking on a marvellous journey to China to find a wonderful tree made of jewels. He had no idea that Mr. Wicker was a magician and could travel through time. And that the tree was sought by others, not least among them the murderous Claggett Chew, a merchant in port and a pirate on the high seas, who also had knowledge of magic. But before Chris succeeded in quest, he would know of all these things and more. And of Mr. Wicker's friends, the sailor Ned Cilley, Becky Boozer, and the African boy Amos, changed from wood to flesh. And Christopher Mason would never be same, after. (Introduction by Arthur Piantadosi)

3Confederate Girl's Diary

By Sarah Morgan Dawson

Sarah Morgan Dawson was a young woman of 20 living in Baton Rouge, Louisiana, when she began this diary. The American Civil War was raging. Though at first the conflict seemed far away, it would eventually be brought home to her in very personal terms. Her family's loyalties were divided. Sarah's father, though he disapproved of secession, declared for the South when Louisiana left the Union. Her eldest brother, who became the family patriarch when his father died in 1861, was for the Union, though he refused to take up arms against his fellow Southerners. The family owned slaves, some of whom are mentioned by name in this diary. Sarah was devoted to the Confederacy, and watched with sorrow and indignation its demise. Her diary, written from March 1862 to June 1865, discourses on topics as normal as household routines and romantic intrigues to those as unsettling as concern for her brothers who fought in the war. Largely self-taught, she describes in clear and inviting prose, fleeing Baton Rouge during a bombardment, suffering a painful spinal injury when adequate medical help was unavailable, the looting of her home by Northern soldiers, the humiliation of life under General Butler in New Orleans, and dealing with privations and displacement in a region torn by war. She was a child of her time and place. Her inability to see the cruelty and indignity of slavery grates harshly on the modern ear. Regardless of how one feels about the Lost Cause, however, Sarah's diary provides a valuable historical perspective on life behind the lines of this bitter conflict. (Introduction by Christine Dufour)

Stories of World War I warfare, published in 1916 in the midst of the war. (That's why names of persons and units are literally "blanked" out.) Alec John Dawson (1872 - 1951), generally known as A. J. Dawson (pseudonyms Major Dawson, Howard Kerr, Nicholas Freydon) was an English author, traveller and novelist. During World War I he attained the rank of Major, and was awarded the MBE and Croix de Guerre in recognition of his work as a military propagandist, a work the listener may want to keep in mind. (Terminology note: "Boche" means the Germans, singular or plural; "Blighty" means hospitalization in England; "The Push" means fighting in the Somme offensive.)<br /><br /> The Battle of the Somme (French: Bataille de la Somme, German: Schlacht an der Somme), also known as the Somme Offensive, was a battle of the First World War fought by the armies of the British and French empires against the German Empire. It took place between 1 July and 18 November 1916 on either side of the River Somme in France. The battle was one of the largest of World War I, in which more than 1,000,000 men were wounded or killed, making it one of humanity's bloodiest battles.... 1 July 1916 was also the worst day in the history of British Army, which had c. 60,000 casualties,... The British Army on the Somme was a mixture of the remains of the pre-war regular army, Territorial Force and the Kitchener Army which was composed of Pals battalions, recruited from the same places and occupations, whose losses had a profound social impact in Britain.... The Battle of the Somme has been called the beginning of modern all-arms warfare, during which Kitchener's Army learned to fight the mass-industrial war, which the continental armies had been engaged in for two years. This view sees the British contribution to the battle as part of a coalition war and part of a process, which took the strategic initiative from the German Army and caused it irreparable damage, leading to its collapse in late 1918. (Wikipedia, Battle Of The Somme) ( Wikipedia and david wales)

5Finn The Wolfhound

By Alec John Dawson

Dawson published over thirty books, the one best remembered today probably being the animal adventure story Finn the Wolfhound (1908)…. His own dog Tynagh and her son Gareth, who was described as the largest and finest specimen of his breed to date, served as the models for Tara and Finn in Finn the Wolfhound (1908). This is probably Dawson’s best-remembered and certainly his most frequently reprinted work: Finn, a champion Irish Wolfhound, is taken from England to Australia where he undergoes a series of adventures, being exhibited as a wild animal in a circus and escaping to live in the outback before eventually finding his old master and saving his life. - Summary by Wikipedia and david wales

6Christmas Outside Of Eden

By Coningsby Dawson

A delightful Christmas fantasy told with inimitable charm and delicate humor. It is "the story the robins tell as they huddle beneath the holly on the Eve of Christmas"—the sensation created by the birth of the first baby, among the animals on earth, the angels in heaven, and even in the mind of the surprised Almighty Himself. The conception of the Deity is a primitive one, as required by the nature of the tale, and the story should be read as a "myth-story." - Publisher's Advertisement

7It Might Have Happened to You

By Coningsby Dawson

This is a frank eyewitness description of the suffering, starvation in particular, that was widely experienced in Central and Eastern Europe in the aftermath of "The Great War". “It is not stating matters too strongly to say that…peace had caused at least as much misery as the four years’ fury of embattled armies.” It is a powerful political and anti-war statement with scant mention of any battle. – Lee Smalley

“Here are boys, all sorts of boys: French, English, Italian, American… These are soldiers’ letters written home. But reading, one finds that he does not think of them as letters at all, but as boys… but the spirit of these letters cannot be defeated. The dead will rise again.” Each letter is introduced by a paragraph or two about the writer. - Summary by Author's Introduction and David Wales

This is a volume of short stories of supernatural fiction by American author Emma Frances Dawson. Not all of the tales depend on ghosts, most of them are much more subtle than that. The author skillfully creates undercurrents, adding a distinct quality to these stories. - Summary by Carolin

10South American Republics, Part I

By Thomas Cleland Dawson

The question most frequently asked me since I began my stay in South America has been: "Why do they have so many revolutions there?" Possibly the events recounted in the following pages may help the reader to answer this for himself. I hope that he will share my conviction that militarism has already definitely disappeared from more than half the continent and is slowly becoming less powerful in the remainder. Constitutional traditions, inherited from Spain and Portugal, implanted a tendency toward disintegration; Spanish and Portuguese tyranny bred in the people a distrust of all rulers and governments; the war of independence brought to the front military adventurers; civil disorders were inevitable, and the search for forms of government that should be final and stable has been very painful. On the other hand, the generous impulse that prompted the movement toward independence has grown into an earnest desire for ordered liberty, which is steadily spreading among all classes. Civic capacity is increasing among the body of South Americans and immigration is raising the industrial level. They are slowly evolving among themselves the best form of government for their special needs and conditions.<br /><br />It is hard to secure from the tangle of events called South American history a clearly defined picture. At the risk of repetition I have tried to tell separately the story of each country, because each has its special history and its peculiar characteristics. All of these states have, however, had much in common and it is only in the case of the larger nations that social and political conditions have been described in detail. (Fragment of the Preface)<br /><br />See the original text for the bibliography and numerous illustrations.

11South American Republics, Part II

By Thomas Cleland Dawson

This history begins when Pizarro and Almagro, Valdivia and Benalcazar, led their desperadoes across the Isthmus to the conquest, massacre, and enslavement of the prosperous and civilised millions who inhabited the Pacific coast of South America. It ends with the United States opening a way through that same Isthmus for the ships, the trade, the capital of all the world; with American engineers laying railroad iron on the imperial highway of the Incas; with British bondholders forgiving stricken Peru's national debt; with their debtor bravely facing the fact of bankruptcy, and turning over to them all its railways. (from the Preface, available in the source text together with the bibliography and numerous pictures)

12Trips in the Life of a Locomotive Engineer

By Henry Dawson

Henry Dawson has written several vignettes of railroad men from the days of steam locomotives. His goal is to show the reader that they are not just rough men, but are also brave and heroic men through descriptions of divers dangers encountered on the tracks. (Summary adapted from the Preface)