===== Ph. D. Dissertation =====

The long title translates as
//A theoretical approach to connectionist learning,  
with applications for speech recognition//.
This is a relatively big document with a number of
relatively new ideas for the time.

   * [[wp>Connectionism|Connectionist learning algorithms]] can be studied as [[wp>stochastic approximations]] and more specifically [[wp>stochastic gradient descent]] algorithms, possibly involving surrogate loss functions (chapters 2 and 3).
   * The performance of these algorithms can be studied using advanced statistical theories such as [[wp>Vladimir Vapnik]]'s [[wp>Structural Risk Minimization]] (chapter 4).
   * The speed of these algorithms can be approached using the methods of numerical optimization (chapter 5.)
   * Complex applications, such as [[wp>speech recognition]], can be addressed using modular learning systems such as Discriminant Hidden Markov Models (chapter 8 and 9).
   * Probabilistic discriminant modular learning systems are often limited by the so-called //label-bias problem// (chapter 10).  Finding a solution took a [[:research:structured|three more years]].
==== ====


<box 99% orange>
Léon Bottou:  //**Une Approche théorique de l'Apprentissage Connexionniste: Applications à la Reconnaissance de la Parole**//, Ph.D. thesis, Université de Paris XI, Orsay, France, 1991.

[[http://leon.bottou.org/publications/djvu/bottou-1991.djvu|bottou-1991.djvu (one big file)]]
[[http://leon.bottou.org/publications/pdf/bottou-1991.pdf|bottou-1991.pdf]]
[[http://leon.bottou.org/publications/psgz/bottou-1991.ps.gz|bottou-1991.ps.gz]]\\
[[http://leon.bottou.org/cgi/djvuserve/publications/djvu/bottou-1991.djvu|bottou-1991.djvu (served page per page)]]
</box>

  @phdthesis{bottou-91a,
    title = {Une Approche th\'eorique de l'Apprentissage Connexionniste: Applications \`a la Reconnaissance de la Parole},
    author = {Bottou, {L\'eon}},
    year = {1991},
    school = {Universit\'{e} de Paris XI},
    address = {Orsay, France},
    url = {http://leon.bottou.org/papers/bottou-91a},
  }