About: Including source code of Threshold Method,SVM,Play Scan and Play detection.

Initial Announcement on mloss.org.

About: mlpy is a Python module for Machine Learning built on top of NumPy/SciPy and of GSL.

New features:

• LibSvm(): pred_probability() now returns probability estimates; pred_values() added
• LibLinear(): pred_values() and pred_probability() added
• dtw_std: squared Euclidean option added
• LCS for series composed by real values (lcs_real()) added
• Documentation

Fix:

• wavelet submodule: cwt(): it returned only real values in morlet and poul
• IRelief(): remove np. in learn()
• fix rfe_kfda and rfe_w2 when p=1

About: A Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Dynamically generates CPU and GPU modules for good performance. Deep Learning Tutorials illustrate deep learning with Theano.

Theano 0.5 (23 February 2012)

Highlight:

• Moved to github: http://github.com/Theano/Theano/
• Old trac ticket moved to assembla ticket: http://www.assembla.com/spaces/theano/tickets
• Theano vision: http://deeplearning.net/software/theano/introduction.html#theano-vision (Many people)
• Theano with GPU works in some cases on Windows now. Still experimental. (Sebastian Urban)
• Faster dot() call: New/Better direct call to cpu and gpu ger, gemv, gemm and dot(vector, vector). (James, Frederic, Pascal)
• C implementation of Alloc. (James, Pascal)
• theano.grad() now also work with sparse variable. (Arnaud)
• Macro to implement the Jacobian/Hessian with theano.tensor.{jacobian,hessian} (Razvan)
• See the Interface changes.

Interface Behavior Changes:

• The current default value of the parameter axis of theano.{max,min,argmax,argmin,max_and_argmax} is now the same as numpy: None. i.e. operate on all dimensions of the tensor. (Frederic Bastien, Olivier Delalleau) (was deprecated and generated a warning since Theano 0.3 released Nov. 23rd, 2010)
• The current output dtype of sum with input dtype [u]int* is now always [u]int64. You can specify the output dtype with a new dtype parameter to sum. The output dtype is the one using for the summation. There is no warning in previous Theano version about this. The consequence is that the sum is done in a dtype with more precision than before. So the sum could be slower, but will be more resistent to overflow. This new behavior is the same as numpy. (Olivier, Pascal)
• When using a GPU, detect faulty nvidia drivers. This was detected when running Theano tests. Now this is always tested. Faulty drivers results in in wrong results for reduce operations. (Frederic B.)

Interface Features Removed (most were deprecated):

• The string modes FAST_RUN_NOGC and STABILIZE are not accepted. They were accepted only by theano.function(). Use Mode(linker='c|py_nogc') or Mode(optimizer='stabilize') instead.
• tensor.grad(cost, wrt) now always returns an object of the "same type" as wrt (list/tuple/TensorVariable). (Ian Goodfellow, Olivier)
• A few tag.shape and Join.vec_length left have been removed. (Frederic)
• The .value attribute of shared variables is removed, use shared.set_value() or shared.get_value() instead. (Frederic)
• Theano config option "home" is not used anymore as it was redundant with "base_compiledir". If you use it, Theano will now raise an error. (Olivier D.)
• scan interface changes: (Razvan Pascanu)
  • The use of return_steps for specifying how many entries of the output to return has been removed. Instead, apply a subtensor to the output returned by scan to select a certain slice.
  • The inner function (that scan receives) should return its outputs and updates following this order: [outputs], [updates], [condition]. One can skip any of the three if not used, but the order has to stay unchanged.

Interface bug fix:

• Rop in some case should have returned a list of one Theano variable, but returned the variable itself. (Razvan)

New deprecation (will be removed in Theano 0.6, warning generated if you use them):

• tensor.shared() renamed to tensor._shared(). You probably want to call theano.shared() instead! (Olivier D.)

Bug fixes (incorrect results):

• On CPU, if the convolution had received explicit shape information, they where not checked at runtime. This caused wrong result if the input shape was not the one expected. (Frederic, reported by Sander Dieleman)
• Theoretical bug: in some case we could have GPUSum return bad value. We were not able to reproduce this problem
  • patterns affected ({0,1}*nb dim, 0 no reduction on this dim, 1 reduction on this dim): 01, 011, 0111, 010, 10, 001, 0011, 0101 (Frederic)
• div by zero in verify_grad. This hid a bug in the grad of Images2Neibs. (James)
• theano.sandbox.neighbors.Images2Neibs grad was returning a wrong value. The grad is now disabled and returns an error. (Frederic)
• An expression of the form "1 / (exp(x) +- constant)" was systematically matched to "1 / (exp(x) + 1)" and turned into a sigmoid regardless of the value of the constant. A warning will be issued if your code was affected by this bug. (Olivier, reported by Sander Dieleman)
• When indexing into a subtensor of negative stride (for instance, x[a:b:-1][c]), an optimization replacing it with a direct indexing (x[d]) used an incorrect formula, leading to incorrect results. (Pascal, reported by Razvan)
• The tile() function is now stricter in what it accepts to allow for better error-checking/avoiding nonsensical situations. The gradient has been disabled for the time being as it only implemented (incorrectly) one special case. The reps argument must be a constant (not a tensor variable), and must have the same length as the number of dimensions in the x argument; this is now checked. (David)

Scan fixes:

• computing grad of a function of grad of scan (reported by Justin Bayer, fix by Razvan) before : most of the time crash, but could be wrong value with bad number of dimensions (so a visible bug) now : do the right thing.
• gradient with respect to outputs using multiple taps (reported by Timothy, fix by Razvan) before : it used to return wrong values now : do the right thing. Note: The reported case of this bug was happening in conjunction with the save optimization of scan that give run time errors. So if you didn't manually disable the same memory optimization (number in the list4), you are fine if you didn't manually request multiple taps.
• Rop of gradient of scan (reported by Timothy and Justin Bayer, fix by Razvan) before : compilation error when computing R-op now : do the right thing.
• save memory optimization of scan (reported by Timothy and Nicolas BL, fix by Razvan) before : for certain corner cases used to result in a runtime shape error now : do the right thing.
• Scan grad when the input of scan has sequences of different lengths. (Razvan, reported by Michael Forbes)
• Scan.infer_shape now works correctly when working with a condition for the number of loops. In the past, it returned n_steps as the length, which is not always true. (Razvan)
• Scan.infer_shape crash fix. (Razvan)

New features:

• AdvancedIncSubtensor grad defined and tested (Justin Bayer)
• Adding 1D advanced indexing support to inc_subtensor and set_subtensor (James Bergstra)
• tensor.{zeros,ones}_like now support the dtype param as numpy (Frederic)
• Added configuration flag "exception_verbosity" to control the verbosity of exceptions (Ian)
• theano-cache list: list the content of the theano cache (Frederic)
• theano-cache unlock: remove the Theano lock (Olivier)
• tensor.ceil_int_div to compute ceil(a / float(b)) (Frederic)
• MaxAndArgMax.grad now works with any axis (The op supports only 1 axis) (Frederic)
  • used by tensor.{max,min,max_and_argmax}
• tensor.{all,any} (Razvan)
• tensor.roll as numpy: (Matthew Rocklin, David Warde-Farley)
• Theano with GPU works in some cases on Windows now. Still experimental. (Sebastian Urban)
• IfElse now allows to have a list/tuple as the result of the if/else branches.
  • They must have the same length and corresponding type (Razvan)
• Argmax output dtype is now int64 instead of int32. (Olivier)
• Added the element-wise operation arccos. (Ian)
• Added sparse dot with dense grad output. (Yann Dauphin)
  • Optimized to Usmm and UsmmCscDense in some case (Yann)
  • Note: theano.dot and theano.sparse.structured_dot() always had a gradient with the same sparsity pattern as the inputs. The new theano.sparse.dot() has a dense gradient for all inputs.
• GpuAdvancedSubtensor1 supports broadcasted dimensions. (Frederic)
• TensorVariable.zeros_like() and SparseVariable.zeros_like()
• theano.sandbox.cuda.cuda_ndarray.cuda_ndarray.device_properties() (Frederic)
• theano.sandbox.cuda.cuda_ndarray.cuda_ndarray.mem_info() return free and total gpu memory (Frederic)
• Theano flags compiledir_format. Keep the same default as before: compiledir_%(platform)s-%(processor)s-%(python_version)s. (Josh Bleecher Snyder)
  • We also support the "theano_version" substitution.
• IntDiv c code (faster and allow this elemwise to be fused with other elemwise) (Pascal)
• Internal filter_variable mechanism in Type. (Pascal, Ian)
  • Ifelse works on sparse.
  • It makes use of gpu shared variable more transparent with theano.function updates and givens parameter.
• Added a_tensor.transpose(axes) axes is optional (James)
  • theano.tensor.transpose(a_tensor, kwargs) We where ignoring kwargs, now it is used as the axes.
• a_CudaNdarray_object[*] = int, now works (Frederic)
• tensor_variable.size (as numpy) computes the product of the shape elements. (Olivier)
• sparse_variable.size (as scipy) computes the number of stored values. (Olivier)
• sparse_variable[N, N] now works (Li Yao, Frederic)
• sparse_variable[M:N, O:P] now works (Li Yao, Frederic, Pascal) M, N, O, and P can be Python int or scalar tensor variables, None, or omitted (sparse_variable[:, :M] or sparse_variable[:M, N:] work).
• tensor.tensordot can now be moved to GPU (Sander Dieleman, Pascal, based on code from Tijmen Tieleman's gnumpy, http://www.cs.toronto.edu/~tijmen/gnumpy.html)
• Many infer_shape implemented on sparse matrices op. (David W.F.)
• Added theano.sparse.verify_grad_sparse to easily allow testing grad of sparse op. It support testing the full and structured gradient.
• The keys in our cache now store the hash of constants and not the constant values themselves. This is significantly more efficient for big constant arrays. (Frederic B.)
• 'theano-cache list' lists key files bigger than 1M (Frederic B.)
• 'theano-cache list' prints an histogram of the number of keys per compiled module (Frederic B.)
• 'theano-cache list' prints the number of compiled modules per op class (Frederic B.)
• The Theano flag "nvcc.fastmath" is now also used for the cuda_ndarray.cu file.
• Add the header_dirs to the hard part of the compilation key. This is currently used only by cuda, but if we use library that are only headers, this can be useful. (Frederic B.)
• The Theano flag "nvcc.flags" is now included in the hard part of the key. This mean that now we recompile all modules for each value of "nvcc.flags". A change in "nvcc.flags" used to be ignored for module that were already compiled. (Frederic B.)
• Alloc, GpuAlloc are not always pre-computed (constant_folding optimization) at compile time if all their inputs are constant. (Frederic B., Pascal L., reported by Sander Dieleman)
• New Op tensor.sort(), wrapping numpy.sort (Hani Almousli)

New optimizations:

• AdvancedSubtensor1 reuses preallocated memory if available (scan, c|py_nogc linker) (Frederic)
• dot22, dot22scalar work with complex. (Frederic)
• Generate Gemv/Gemm more often. (James)
• Remove scan when all computations can be moved outside the loop. (Razvan)
• scan optimization done earlier. This allows other optimizations to be applied. (Frederic, Guillaume, Razvan)
• exp(x) * sigmoid(-x) is now correctly optimized to the more stable form sigmoid(x). (Olivier)
• Added Subtensor(Rebroadcast(x)) => Rebroadcast(Subtensor(x)) optimization. (Guillaume)
• Made the optimization process faster. (James)
• Allow fusion of elemwise when the scalar op needs support code. (James)
• Better opt that lifts transpose around dot. (James)

Crashes fixed:

• T.mean crash at graph building time. (Ian)
• "Interactive debugger" crash fix. (Ian, Frederic)
• Do not call gemm with strides 0, some blas refuse it. (Pascal Lamblin)
• Optimization crash with gemm and complex. (Frederic)
• GPU crash with elemwise. (Frederic, some reported by Chris Currivan)
• Compilation crash with amdlibm and the GPU. (Frederic)
• IfElse crash. (Frederic)
• Execution crash fix in AdvancedSubtensor1 on 32 bit computers. (Pascal)
• GPU compilation crash on MacOS X. (Olivier)
• Support for OSX Enthought Python Distribution 7.x. (Graham Taylor, Olivier)
• When the subtensor inputs had 0 dimensions and the outputs 0 dimensions. (Frederic)
• Crash when the step to subtensor was not 1 in conjunction with some optimization. (Frederic, reported by Olivier Chapelle)
• Runtime crash related to an optimization with subtensor of alloc (reported by Razvan, fixed by Frederic)
• Fix dot22scalar cast of integer scalars (Justin Bayer, Frederic, Olivier)
• Fix runtime crash in gemm, dot22. FB
• Fix on 32bits computer: make sure all shape are int64.(Olivier)
• Fix to deque on python 2.4 (Olivier)
• Fix crash when not using c code (or using DebugMode) (not used by default) with numpy 1.6*. Numpy has a bug in the reduction code that made it crash. (Pascal)
• Crashes of blas functions (Gemv on CPU; Ger, Gemv and Gemm on GPU) when matrices had non-unit stride in both dimensions (CPU and GPU), or when matrices had negative strides (GPU only). In those cases, we are now making copies. (Pascal)
• More cases supported in AdvancedIncSubtensor1. (Olivier D.)
• Fix crash when a broadcasted constant was used as input of an elemwise Op and needed to be upcasted to match the op's output. (Reported by John Salvatier, fixed by Pascal L.)
• Fixed a memory leak with shared variable (we kept a pointer to the original value) (Ian G.)

Known bugs:

• CAReduce with nan in inputs don't return the good output (Ticket <https://www.assembla.com/spaces/theano/tickets/763>_).
  • This is used in tensor.{max,mean,prod,sum} and in the grad of PermuteRowElements.

Sandbox:

• cvm interface more consistent with current linker. (James)
• Now all tests pass with the linker=cvm flags.
• vm linker has a callback parameter. (James)
• review/finish/doc: diag/extract_diag. (Arnaud Bergeron, Frederic, Olivier)
• review/finish/doc: AllocDiag/diag. (Arnaud, Frederic, Guillaume)
• review/finish/doc: MatrixInverse, matrix_inverse. (Razvan)
• review/finish/doc: matrix_dot. (Razvan)
• review/finish/doc: det (determinent) op. (Philippe Hamel)
• review/finish/doc: Cholesky determinent op. (David)
• review/finish/doc: ensure_sorted_indices. (Li Yao)
• review/finish/doc: spectral_radius_boud. (Xavier Glorot)
• review/finish/doc: sparse sum. (Valentin Bisson)
• review/finish/doc: Remove0 (Valentin)
• review/finish/doc: SquareDiagonal (Eric)

Sandbox New features (not enabled by default):

• CURAND_RandomStreams for uniform and normal (not picklable, GPU only) (James)
• New sandbox.linalg.ops.pinv(pseudo-inverse) op (Razvan)

Documentation:

• Many updates. (Many people)
• Updates to install doc on MacOS. (Olivier)
• Updates to install doc on Windows. (David, Olivier)
• Doc on the Rop function (Ian)
• Added how to use scan to loop with a condition as the number of iteration. (Razvan)
• Added how to wrap in Theano an existing python function (in numpy, scipy, ...). (Frederic)
• Refactored GPU installation of Theano. (Olivier)

Others:

• Better error messages in many places. (Many people)
• PEP8 fixes. (Many people)
• Add a warning about numpy bug when using advanced indexing on a tensor with more than 232 elements (the resulting array is not correctly filled and ends with zeros). (Pascal, reported by David WF)
• Added Scalar.ndim=0 and ScalarSharedVariable.ndim=0 (simplify code) (Razvan)
• New min_informative_str() function to print graph. (Ian)
• Fix catching of exception. (Sometimes we used to catch interrupts) (Frederic, David, Ian, Olivier)
• Better support for utf string. (David)
• Fix pydotprint with a function compiled with a ProfileMode (Frederic)
  • Was broken with change to the profiler.
• Warning when people have old cache entries. (Olivier)
• More tests for join on the GPU and CPU. (Frederic)
• Do not request to load the GPU module by default in scan module. (Razvan)
• Fixed some import problems. (Frederic and others)
• Filtering update. (James)
• On Windows, the default compiledir changed to be local to the computer/user and not transferred with roaming profile. (Sebastian Urban)
• New theano flag "on_shape_error". Defaults to "warn" (same as previous behavior): it prints a warning when an error occurs when inferring the shape of some apply node. The other accepted value is "raise" to raise an error when this happens. (Frederic)
• The buidbot now raises optimization/shape errors instead of just printing a warning. (Frederic)
• better pycuda tests (Frederic)
• check_blas.py now accept the shape and the number of iteration as parameter (Frederic)
• Fix opt warning when the opt ShapeOpt is disabled (enabled by default) (Frederic)
• More internal verification on what each op.infer_shape return. (Frederic, James)
• Argmax dtype to int64 (Olivier)
• Improved docstring and basic tests for the Tile Op (David).

About: A mutual information library for C and Mex bindings for MATLAB. Aimed at feature selection, and provides simple methods to calculate mutual information, conditional mutual information, entropy, conditional entropy, and Renyi entropy/mutual information. Works with discrete distributions, and expects column vectors of features.

Updated documentation & link to JMLR publication.

About: FEAST provides implementations of common mutual information based filter feature selection algorithms (mim, mifs, mrmr, cmim, icap, jmi, disr, fcbf, etc), and an implementation of RELIEF.

Initial Announcement on mloss.org.

About: NaN-toolbox is a statistics and machine learning toolbox for handling data with and without missing values.

Changes in v.2.5.2 - faster version of quantile if multiple quantiles are requested - removes the dependency on ZLIB and thus - fixes "pkg install nan" for Octave on Windows - a number of minor improvements

For details see the CHANGELOG at http://pub.ist.ac.at/~schloegl/matlab/NaN/CHANGELOG

About: MATLAB toolbox for advanced Brain-Computer Interface (BCI) research.

Initial Announcement on mloss.org.

About: Python module to ease pattern classification analyses of large datasets. It provides high-level abstraction of typical processing steps (e.g. data preparation, classification, feature selection, [...]

• 2.0.0 (Mon, Dec 19 2011)

This release aggregates all the changes occurred between official releases in 0.4 series and various snapshot releases (in 0.5 and 0.6 series). To get better overview of high level changes see :ref:release notes for 0.5 <chap_release_notes_0.5> and :ref:0.6 <chap_release_notes_0.6> as well as summaries of release candidates below

• Fixes (23 BF commits)

  • significance level in the right tail was fixed to include the value tested -- otherwise resulted in optimistic bias (or absurdly high significance in improbable case if all estimates having the same value)
  • compatible with the upcoming IPython 0.12 and renamed sklearn (Fixes #57)
  • do not double-train slave classifiers while assessing sensitivities (Fixes #53)

• Enhancements (30 ENH + 3 NF commits)

  • resolving voting ties in kNN based on mean distance, and randomly in SMLR
  • :class:kNN's ca.estimates now contains dictionaries with votes for each class
  • consistent zscoring in :class:Hyperalignment

• 2.0.0~rc5 (Wed, Oct 19 2011)

• Major: to allow easy co-existence of stable PyMVPA 0.4.x, 0.6 development mvpa module was renamed into mod:mvpa2.

• Fixes

  • compatible with the new Shogun 1.x series
  • compatible with the new h5py 2.x series
  • mvpa-prep-fmri -- various compatibility fixes and smoke testing
  • deepcopying :class:SummaryStatistics during add

• Enhancements

  • tutorial uses :mod:mvpa2.tutorial_suite now
  • better suppression of R warnings when needed
  • internal attributes of many classes were exposed as properties
  • more unification of __repr__ for many classes

• 0.6.0~rc4 (Wed, Jun 14 2011)

• Fixes

  • Finished transition to :mod:nibabel conventions in plot_lightbox
  • Addressed :mod:matplotlib.hist API change
  • Various adjustments in the tests batteries (:mod:nibabel 1.1.0 compatibility, etc)

• New functionality

  • Explicit new argument flatten to from_wizard -- default behavior changed if mapper was provided as well

• Enhancements

  • Elaborated __str__ and __repr__ for some Classifiers and Measures

• 0.6.0~rc3 (Thu, Apr 12 2011)

• Fixes

  • Bugfixes regarding the interaction of FlattenMapper and BoxcarMapper that affected event-related analyses.
  • Splitter now handles attribute value None for splitting properly.
  • GNBSearchlight handling of
    roi_ids.
  • More robust detection of mod:scikits.learn and :mod:nipy externals.

• New functionality

  • Added a Repeater node to yield a dataset multiple times and
    Sifter node to exclude some datasets. Consequently, the "nosplitting" mode of Splitter got removed at the same time.
  • :file:tools/niils -- little tool to list details (dimensionality, scaling, etc) of the files in nibabel-supported formats.

• Enhancements

  • Numerous documentation fixes.
  • Various improvements and increased flexibility of null distribution estimation of Measures.
  • All attribute are now reported in sorted order when printing a dataset.
  • fmri_dataset now also stores the input image type.
  • Crossvalidation can now take a custom Splitter instance. Moreover, the default splitter of CrossValidation is more robust in terms of number and type of created splits for common usage patterns (i.e. together with partitioners).
  • CrossValidation takes any custom Node as errorfx argument.
  • ConfusionMatrix can now be used as an errorfx in Crossvalidation.
  • LOE(ACC): Linear Order Effect in ACC was added to
    ConfusionMatrix to detect trends in performances across splits.
  • A Node s postproc is now accessible as a property.
  • RepeatedMeasure has a new 'concat_as' argument that allows results to be concatenated along the feature axis. The default behavior, stacking as multiple samples, is unchanged.
  • Searchlight now has the ability to mark the center/seed of an ROI in with a feature attribute in the generated datasets.
  • debug takes args parameter for delayed string comprehensions. It should reduce run-time impact of debug() calls in regular, non -O mode of Python operation.
  • String summaries and representations (provided by __str__ and __repr__) were made more exhaustive and more coherent. Additional properties to access initial constructor arguments were added to variety of classes.

• Internal changes

  • New debug target STDOUT to allow attaching metrics (e.g. traceback, timestamps) to regular output printed to stdout

  • New set of decorators to help with unittests

  • @nodebug to disable specific debug targets for the duration of the test.

  • @reseed_rng to guarantee consistent random data given initial seeding.

  • @with_tempfile to provide a tempfile name which would get removed upon completion (test success or failure)

  • Dropping daily testing of maint/0.5 branch -- RIP.

  • Collection s were provided with adequate (deep|)copy. And Dataset was refactored to use Collection s copy method.

  • update-* Makefile rules automatically should fast-forward corresponding website-updates branch

  • MVPA_TESTS_VERBOSITY controls also :mod:numpy warnings now.

  • Dataset.__array__ provides original array instead of copy (unless dtype is provided)

Also adapts changes from 0.4.6 and 0.4.7 (see corresponding changelogs).

• 0.6.0~rc2 (Thu, Mar 3 2011)

• Various fixes in the mvpa.atlas module.

• 0.6.0~rc1 (Thu, Feb 24 2011)

• Many, many, many

• For an overview of the most drastic changes :ref:see constantly evolving release notes for 0.6 <chap_release_notes_0.6>

• 0.5.0 (sometime in March 2010)

This is a special release, because it has never seen the general public. A summary of fundamental changes introduced in this development version can be seen in the :ref:release notes <chap_release_notes_0.5>.

Most notably, this version was to first to come with a comprehensive two-day workshop/tutorial.

• 0.4.7 (Tue, Mar 07 2011) (Total: 12 commits)

A bugfix release

• Fixed

  • Addressed the issue with input NIfTI files having scl_ fields set: it could result in incorrect analyses and map2nifti-produced NIfTI files. Now input files account for scaling/offset if scl_ fields direct to do so. Moreover upon map2nifti, those fields get reset.
  • :file:doc/examples/searchlight_minimal.py - best error is the minimal one

• Enhancements

  • :class:~mvpa.clfs.gnb.GNB can now tolerate training datasets with a single label
  • :class:~mvpa.clfs.meta.TreeClassifier can have trailing nodes with no classifier assigned

• 0.4.6 (Tue, Feb 01 2011) (Total: 20 commits)

A bugfix release

• Fixed (few BF commits):

  • Compatibility with numpy 1.5.1 (histogram) and scipy 0.8.0 (workaround for a regression in legendre)
  • Compatibility with libsvm 3.0
  • :class:~mvpa.clfs.plr.PLR robustification

• Enhancements

  • Enforce suppression of numpy warnings while running unittests. Also setting verbosity >= 3 enables all warnings (Python, NumPy, and PyMVPA)
  • :file:doc/examples/nested_cv.py example (adopted from 0.5)
  • Introduced base class :class:~mvpa.clfs.base.LearnerError for classifiers' exceptions (adopted from 0.5)
  • Adjusted example data to live upto nibabel's warranty of NIfTI standard-compliance
  • More robust operation of MC iterations -- skip iterations where classifier experienced difficulties and raise an exception (e.g. due to degenerate data)

About: Scilab Pattern Recognition Toolbox is a toolbox developed for Scilab software, and is used in pattern recognition, machine learning and the related field. It is developed for the purpose of education and research.

Initial Announcement on mloss.org.

About: Multicore/distributed large scale machine learning framework.

Update version.

About: FLANN is a library for performing fast approximate nearest neighbor searches in high dimensional spaces. It contains a collection of algorithms we found to work best for nearest neighbor search.

See project page for changes.

About: GritBot is an data cleaning and outlier/anomaly detection program.

Initial Announcement on mloss.org.

About: Cubist is the regression counterpart to the C5.0 decision tree tool.

Initial Announcement on mloss.org.

About: C5.0 is the successor of the C4.5 decision tree algorithm/tool. In particular, it is faster and more memory-efficient.

Initial Announcement on mloss.org.

About: The K-tree is a scalable approach to clustering inspired by the B+-tree and k-means algorithms.

Release of K-tree implementation in Python. This is targeted at a research and rapid prototyping audience.

About: A fast and scalable graph-based clustering algorithm based on the eigenvectors of the nonlinear 1-Laplacian.

• fixed bug occuring when input graph is disconnected
• reduced memory usage when input graph has large number of disconnected components
• more user-friendly usage of main method OneSpectralClustering
• faster computation of eigenvector initialization + now thresholded according to multicut-criterion
• several internal optimizations