Barbara Hammer Livres

Folding networks, a generalisation of recurrent neural networks to tree structured inputs, are investigated as a mechanism to learn regularities on classical symbolic data, for example. The architecture, the training mechanism, and several applications in different areas are explained. Afterwards a theoretical foundation, proving that the approach is appropriate as a learning mechanism in principle, is Their universal approximation ability is investigated- including several new results for standard recurrent neural networks such as explicit bounds on the required number of neurons and the super Turing capability of sigmoidal recurrent networks. The information theoretical learnability is examined - including several contribution to distribution dependent learnability, an answer to an open question posed by Vidyasagar, and a generalisation of the recent luckiness framework to function classes. Finally, the complexity of training is considered - including new results on the loading problem for standard feedforward networks with an arbitrary multilayered architecture, a correlated number of neurons and training set size, a varying number of hidden neurons but fixed input dimension, or the sigmoidal activation function, respectively.

The human brain's remarkable ability to understand, interpret, and produce language primarily relies on the left hemisphere. Language acquisition is innate, as demonstrated by specific language impairment (SLI), which indicates a lack of grammaticality sense. Language is characterized by strong compositionality and structure, linking biological neural networks to the processing and generation of high-level symbolic structures. In contrast, artificial neural networks and logic do not share this close connection. Two major paradigms in artificial intelligence—symbolic inference mechanisms and statistical machine learning—each have distinct strengths and weaknesses. Statistical methods provide flexible and effective tools for handling corrupted or noisy data, uncertainty, and missing information, as seen in robotics, medical measurements like EEG and EKG, and financial indices. However, these models often function as black boxes, complicating the integration of prior knowledge and human inspection while struggling with complex structures of objects, classes, and relations. Symbolic mechanisms excel in intuitive human-machine interaction and integrating complex prior knowledge, but they are less effective in managing uncertainty and noise in large-scale real-world data sets. Ultimately, the strengths and weaknesses of these two approaches complement each other.

HAMMER! is the first book by influential filmmaker Barbara Hammer, whose life and work have inspired a generation of queer, feminist, and avant-garde artists and filmmakers. The wild days of non-monogamy in the 1970s, the development of a queer aesthetic in the 1980s, the fight for visibility during the culture wars of the 1990s, her search for meaning as she contemplates mortality in the past ten years—HAMMER! includes texts from these periods, new writings, and fully contextualized film stills to create a memoir as innovative and disarming as her work has always been.Barbara Hammer has made over eighty films and video works over the past forty years. Her experimental films of the 1970s often dealt with taboo subjects such as menstruation, female orgasm, and lesbian sexuality. In the 1980s she used optical printing to explore perception and the fragility of 16mm film life itself. Her documentaries tell the stories of marginalized peoples who have been hidden from history. Her most recent work, A Horse is Not a Metaphor, won the 2009 Teddy Award for Best Short Film at the Berlin International Film Festival. A retrospective screening of her work will be presented at the Museum of Modern Art in spring 2010 and will travel to the Reina Sophia in Madrid and the Tate Modern in London.

Die amerikanische Künstlerin Barbara Hammer (geb. 1939) gilt als eine der Pionierinnen des homosexuellen Dokumentar- und Experimentalfilms, ihre Arbeiten zählen zu den frühesten und umfangreichsten Darstellungen lesbischer Identität, Liebe und Sexualität. Darüber hinaus hat sich die Künstlerin mit weiteren Genres beschäftigt, die erstmals umfassend dokumentiert werden. Seit den 1960er Jahren drehte die feministische, in New York lebende Künstlerin Barbara Hammer nicht nur experimentelle Filme, für die sie mehrfach ausgezeichnet wurde, sondern widmet sich auch Zeichnungen, Collagen, Installationen und der Malerei. In ihren umfangreichen Materialexperimenten dreht sich ihre künstlerische Erzählung um die zentralen Themen der lesbischen Sexualität, Intimität und Empfindung, Beziehungen und Prägungen. In einer sich über fünf Jahrzehnte spannenden Zusammenstellung bekannter und bislang unbekannter Arbeiten wird die enorme Bandbreite der Künstlerin sichtbar und unterstreicht ihre eminente Bedeutung für die homosexuelle Kunstgeschichte.