.. index::
    schedule

.. _`sec:organization`:

Organization
============

This course is about computer science and artificial intelligence. 
The main topics are:

+ python programming tools and methods (~16h)
+ algorithmic (~16h) focussed on graphs and search problems
+ deep learning basics (~16h) focussed on forward neural networks with physical informed net applications
+ reinforcement learning (~16h) focused on Markov decision processes

The goal is to give you the fundamentals to build on, these subjects can not be covered in depth in only few hours. 



Schedule
========

+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      TOOLS & METHODS                                     |          session                    |              duration              |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     course ojectives, general information                |               1                     |              0.5                   |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     uv                                                   |                                     |              0.5                   |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     vscode                                               |                                     |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     basics                                               |                                     |              2                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     profiling                                            |               2                     |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     testing                                              |                                     |              2                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     useful modules                                       |                                     |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     useful modules                                       |               3                     |              2                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     type hints                                           |                                     |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     git                                                  |                                     |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      ALGORITHMS                                          |          session                    |              duration              |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     complexity                                           |                4                    |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     recursion                                            |                                     |              3                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     recursion                                            |                5                    |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     divide & conquer                                     |                                     |              3                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     dynamic programming                                  |                6                    |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     complexity                                           |                7                    |              1                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     graphs                                               |                                     |              3                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      ARTIFICIAL INTELLIGENCE                             |          session                    |              duration              |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     neural networks                                      |            8-9                      |              8                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     physics informed neural networks                     |            10-11                    |              8                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     state models                                         |            12                       |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     Markov decision processes                            |            13                       |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|     reinforcement learning                               |            14-15                    |              8                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      OTHER                                               |          session                    |              duration              |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      projects                                            |            1st 1/2 group            |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      documentation + lose ends                           |            2nd 1/2 group            |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+
|      student presentations                               |              16                     |              4                     |
+----------------------------------------------------------+-------------------------------------+------------------------------------+

In addition to all the non listed demos, below the exercise list (few at the beginning, a lot later on):

TOOLS & METHODS

Python built-in types

   + :ref:`student grade data type <ex:student_grade>`
   + :ref:`project group data type <ex:project_groups>`

Functions

   + :ref:`bank account function <ex:bank_account>`

Profiling

   + :ref:`profiling data size <ex:data_size>`
   + :ref:`memory usage <ex:memory_usage>`

Testing:

    + :ref:`fixture <ex:fixture>`
    + :ref:`project assignment app <ex:assignement_app>`
    + :ref:`test assignment algorithm <ex:assignment_algo>`
    + :ref:`type of testing <ex:type_tests>`

Useful modules:

   + :ref:`decorator <ex:decorator>`
   + :ref:`wraps <ex:wraps>`
   + :ref:`cache <ex:cache>` 
   + :ref:`defaultdict <ex:defaultdict>`
   + :ref:`heapq <ex:heapq>`   
   + :ref:`itertools <ex:itertools>`

Type hints:

    + :ref:`abstract type first <ex:abstract_type_iterable>`
    + :ref:`abstract type second <ex:abstract_type_generator>`
    + :ref:`abstract type third <ex:abstract_type_callable>`

Protocols:

    +  :ref:`protocol <ex:protocol>`

Aliases:

    + :ref:`type alias first <ex:type_alias>`
    + :ref:`type alias second <ex:type_alias_2>`
    + :ref:`new type <ex:new_type>`


ALGORITHMIC

Complexity:

   + :ref:`Matrix product complexity <ex:matrix_dot_complexity>`
   + :ref:`Check uniqueness complexity <ex:unique_complexity>`
   + :ref:`Upper triangular system solving complexity <ex:upper_complexity>`
   + :ref:`Fairest assignment complexity  <ex:fairest_assign_complexity>`

Recursion:

   + :ref:`Factorial <ex:factorial>`
   + :ref:`Horner polynomial evaluation <ex:horner>`
   + :ref:`Laplace determinant <ex:determinant>`
   + :ref:`Permutations <ex:permutation>`
   + :ref:`Cartesian product <ex:cartesian>`

Divide & conquer:

   + :ref:`Quicksort <ex:quicksort>`
   + :ref:`Merge sort <ex:mergesort>`
   + :ref:`Bisection insertion <ex:bisection>`

Dynamic programming:

    + :ref:`Length of the longest common subsequence <ex:llcs>`
    + :ref:`Longest non-decreasing subsequence <ex:lnds>`

Graphs:

    + :ref:`Graph structure <ex:graphs_structure>`
    + :ref:`Graph transpose <ex:graphs_transpose>`
    + :ref:`Graph traversal <ex:graphs_traversal_hand>`
    + :ref:`Graph Depth First recursive and iterative <ex:graphs_DFS_recursive_iterative>`
    + :ref:`Graph Breadth First and Uniform Cost <ex:graphs_traversal_BF_UC>`
    + :ref:`Graph Uniform Cost Search <ex:graphs_UCS>`
    + :ref:`Shortest path in DAG <ex:shortest_path_dag>`
    + :ref:`Topological order <ex:topological>`


ARTIFICIAL INTELLIGENCE

State models:

    + :ref:`Magic tram state problem <ex:state_models_magic_tram>`
    + :ref:`Swamp isle state problem <ex:state_models_swamp_isle>`

Markov decision processes:

    + :ref:`MDP graph (game)  <ex:mdp_game_graph>`
    + :ref:`MDP types/structures <ex:mdp_python_structure>`
    + :ref:`Expectation <ex:preliminary_mdp_expected>`
    + :ref:`MDP value (game) <ex:mdp_value>`    
    + :ref:`MDP policy evaluation (game) <ex:mdp_policy_evaluation>`
    + :ref:`MDP value iteration (game) <ex:mdp_value_iteration>`

    + :ref:`MDP example game <ex:mdp_game_implementation>`
    + :ref:`MDP example magic tram <ex:mdp_tram_implementation>`
    + :ref:`MDP example swamp isle <ex:mdp_swamp_implementation>`

Reinforcement learning:

   + :ref:`model-based Monte-Carlo (game)  <ex:rl_model_based>`
   + :ref:`model-free Monte-Carlo (game)  <ex:rl_model_free_MC>`
   + :ref:`sarsa (game)  <ex:rl_model_free_sarsa>`
   + :ref:`q-learning (game)  <ex:rl_model_free_qlearning>`

   + :ref:`Environment in reinforcement learning <ex:rl_environment>`
   + :ref:`Reinforcement learning algorithms <ex:rl_algo>`
   + :ref:`Reinforcement leaning magic tram <ex:rl_tram>`
   + :ref:`Reinforcement leaning swamp isle <ex:rl_swamp>`

Forward Neural Networks:

    + :ref:`Examples regression and multi-class classification   <ex:example_regression_classification>`
    + :ref:`Number of parameters in a FNN <ex:nb_parameters>`
    + :ref:`Activation functions  <ex:activation>`
    + :ref:`Accuracy evaluation  <ex:mean_accuracy>`
    + :ref:`Output derivative <ex:output_derivative>` 
    + :ref:`Numpy basics <ex:numpy>` 
    + :ref:`Neural network jacobian <ex:jacobian>`
    + :ref:`Back-propagation and gradient descent <ex:back-prop>`    
    + :ref:`FNN example R to R <`ex:ex_fnn_R_to_R`>`  

Physics Informed Neural Networks:

    + :ref:`Unary computation graph  <ex:computation_graph_unary>`
    + :ref:`Binary (division) computation graph <ex:ad_div>`
    + :ref:`First derivative automatic differentiation <ex:ad_first>`
    + :ref:`Higher order derivative automatic differentiation  <ex:ad_mult_add_higher>`



.. + tools and methods 1 & 2: :ref:`coding environment <sec:ide>`, :ref:`package management <sec:uv>`, :ref:`python basics <sec:basics>`
.. + tools and methods 3 & algorithmic 1: profiling & complexity
.. + tools and methods 4: testing 
.. + algorithmic 1: recursion 
.. + algorithmic 2: divide & conquer
.. + tools and methods 5 & 6: essential standard modules
.. + algorithmic 3 & 4: graphs
.. + tools and methods 7: type hints and git
.. + algorithmic 5 & 6 & 7: dynamic programming
.. + tools and methods 8: documentation