NACLab · ago109 · Dec 6, 2025 · Jul 24, 2025 · Jul 24, 2025 · Aug 8, 2025
diff --git a/CITATION.cff b/CITATION.cff
@@ -6,10 +6,12 @@ authors:
     orcid: https://orcid.org/0000-0002-2590-1310
   - family-names: Gebhardt
     given-names: William
+    orcid: https://orcid.org/0009-0008-7456-6556
   - family-names: Mali
     given-names: Ankur
+    orcid: https://orcid.org/0000-0001-5813-3584
 title: "ngc-learn"
-version: 1.0.0
+version: 3.0.0
 identifiers:
   - type: doi
     value: 10.5281/zenodo.6605728

diff --git a/README.md b/README.md
@@ -32,7 +32,7 @@ ngc-learn requires:
 1) Python (>=3.10)
 2) NumPy (>=1.22.0)
 3) SciPy (>=1.7.0)
-4) ngcsimlib (>=1.0.1), (visit official page <a href="https://github.com/NACLab/ngc-sim-lib">here</a>)
+4) ngcsimlib (>=3.0.0), (visit official page <a href="https://github.com/NACLab/ngc-sim-lib">here</a>)
 5) JAX (>=0.4.28) (to enable GPU use, make sure to install one of the CUDA variants)
 <!--
 5) scikit-learn (>=1.3.1) if using `ngclearn.utils.density`
@@ -42,7 +42,7 @@ ngc-learn requires:
 -->
 
 ---
-ngc-learn 2.0.3 and later require Python 3.10 or newer as well as ngcsimlib >=1.0.1.
+ngc-learn 3.0.0 and later require Python 3.10 or newer as well as ngcsimlib >=3.0.0.
 ngc-learn's plotting capabilities (routines within `ngclearn.utils.viz`) require
 Matplotlib (>=3.8.0) and imageio (>=2.31.5) and both plotting and density estimation
 tools (routines within ``ngclearn.utils.density``) will require Scikit-learn (>=0.24.2).
@@ -75,7 +75,7 @@ Python 3.11.4 (main, MONTH  DAY YEAR, TIME) [GCC XX.X.X] on linux
 Type "help", "copyright", "credits" or "license" for more information.
 >>> import ngclearn
 >>> ngclearn.__version__
-'2.0.3'
+'3.0.0'
 ```
 
 <i>Note:</i> For access to the previous Tensorflow-2 version of ngc-learn (of
@@ -122,7 +122,7 @@ $ python install -e .
 </pre>
 
 **Version:**<br>
-2.0.3 <!--1.2.3-Beta--> <!-- -Alpha -->
+3.0.0 <!--1.2.3-Beta--> <!-- -Alpha -->
 
 Author:
 Alexander G. Ororbia II<br>

diff --git a/docs/images/museum/harmonium/rbm_arch.jpg b/docs/images/museum/harmonium/rbm_arch.jpg
diff --git a/docs/images/museum/harmonium/rbm_recon.jpg b/docs/images/museum/harmonium/rbm_recon.jpg
diff --git a/docs/images/museum/harmonium/receptive_fields.jpg b/docs/images/museum/harmonium/receptive_fields.jpg
diff --git a/docs/images/museum/harmonium/samples_0.jpg b/docs/images/museum/harmonium/samples_0.jpg
diff --git a/docs/images/museum/harmonium/samples_1.jpg b/docs/images/museum/harmonium/samples_1.jpg
diff --git a/docs/images/museum/harmonium/samples_2.jpg b/docs/images/museum/harmonium/samples_2.jpg
diff --git a/docs/images/tutorials/neurocog/gmm_fit.jpg b/docs/images/tutorials/neurocog/gmm_fit.jpg
diff --git a/docs/images/tutorials/neurocog/gmm_samples.jpg b/docs/images/tutorials/neurocog/gmm_samples.jpg
diff --git a/docs/index.rst b/docs/index.rst
@@ -5,10 +5,7 @@
 Welcome to ngc-learn's documentation!
 =====================================
 
-**ngc-learn** is a Python library for building, simulating, and analyzing
-biomimetic computational models, arbitrary predictive processing/coding models,
-and spiking neural networks. This toolkit is built on top of 
-`JAX <https://github.com/google/jax>`_ and is distributed under the 3-Clause BSD license.
+**ngc-learn** is a Python library for building, simulating, and analyzing biomimetic and NeuroAI computational models, arbitrary predictive processing/coding models, spiking neural networks, and general dynamical systems. This toolkit is built on top of `JAX <https://github.com/google/jax>`_ and is distributed under the 3-Clause BSD license.
 
 .. toctree::
    :maxdepth: 1
@@ -23,6 +20,7 @@ and spiking neural networks. This toolkit is built on top of
 
   tutorials/intro
   tutorials/theory
+  tutorials/configuration/index
   tutorials/index
   tutorials/neurocog/index
 
@@ -52,9 +50,10 @@ and spiking neural networks. This toolkit is built on top of
 
 .. toctree::
   :maxdepth: 1
-  :caption: Papers that use NGC-Learn
+  :caption: NGC-Learn Papers & Media
 
   ngclearn_papers
+  ngclearn_talks
 
 Indices and tables
 ==================

diff --git a/docs/installation.md b/docs/installation.md
@@ -1,65 +1,41 @@
 # Installation
 
-**ngc-learn** officially supports Linux on Python 3. It can be run with or
-without a GPU.
+**ngc-learn** officially supports Linux on Python 3. It can be run with or without a GPU.
 
-<i>Setup:</i> <a href="https://github.com/NACLab/ngc-learn">ngc-learn</a>,
-in its entirety (including its supporting utilities),
-requires that you ensure that you have installed the following base dependencies in
-your system. Note that this library was developed and tested on Ubuntu 22.04 (and earlier versions on 18.04/20.04).
-Specifically, ngc-learn requires:
+<i>Setup:</i> <a href="https://github.com/NACLab/ngc-learn">NGC-Learn</a>, in its entirety (including its supporting utility sub-packages), requires that you ensure that you have installed the following base dependencies in your system. Note that this library was developed and tested on Ubuntu 22.04 (with much earlier versions on Ubuntu 18.04/20.04). 
+Specifically, NGC-Learn requires:
 * Python (>=3.10)
-* ngcsimlib (>=1.0.1), (<a href="https://github.com/NACLab/ngc-sim-lib">official page</a>)
+* ngcsimlib (>=3.0.0), (<a href="https://github.com/NACLab/ngc-sim-lib">official page</a>)
 * NumPy (>=1.22.0)
 * SciPy (>=1.7.0)
 * JAX (>= 0.4.28; and jaxlib>=0.4.28) <!--(tested for cuda 11.8)-->
 * Matplotlib (>=3.8.0), (for `ngclearn.utils.viz`)
 * Scikit-learn (>=1.6.1), (for `ngclearn.utils.patch_utils` and `ngclearn.utils.density`)
 
-Note that the above requirements are taken care of if one installs ngc-learn
-through either `pip`. One can either install the CPU version of ngc-learn (if no JAX is
-pre-installed or only the CPU version of JAX is installed currently) via
+Note that the above requirements are taken care of if one installs NGC-Learn through either `pip`. One can either install the CPU version of NGC-Learn (if no JAX is pre-installed or only the CPU version of JAX is currently installed) via: 
 ```console
 $ pip install ngclearn
 ```
 
-or install the GPU version of ngc-learn by first installing the
-<a href="https://jax.readthedocs.io/en/latest/installation.html">CUDA 12
-version of JAX</a> before running the above pip command.
+or install the GPU version of NGC-Learn by first installing the <a href="https://jax.readthedocs.io/en/latest/installation.html">CUDA 12 version of JAX</a> before running the above pip command.
 
-Alternatively, one may locally, step-by-step (see below), install and setup
-ngc-learn from source after pulling from the repo.
+Alternatively, one may locally, step-by-step (see below), install and setup NGC-Learn from source after pulling from the repo. 
 
-Note that installing the official pip package without any form of JAX installed
-on your system will default to downloading the CPU version of ngc-learn (see
-below for installing the GPU version).
+Note that installing the official pip package without any form of JAX installed on your system will default to downloading the CPU version of NGC-Learn (see below for installing the GPU version).
 
 ## Install from Source
 
-0. Install ngc-sim-lib first (as an editable install); visit the repo 
-https://github.com/NACLab/ngc-sim-lib for details.
+1. Install NGC-Sim-Lib first (as an editable install); visit the repo https://github.com/NACLab/ngc-sim-lib for details.
 
-1. Clone the ngc-learn repository:
+2. Clone the NGC-Learn repository: 
 ```console
 $ git clone https://github.com/NACLab/ngc-learn.git
 $ cd ngc-learn
 ```
 
-2. (<i>Optional</i>; only for GPU version) Install JAX for either CUDA 12 , depending
-   on your system setup. Follow the
-   <a href="https://jax.readthedocs.io/en/latest/installation.html">installation instructions</a>
-   on the official JAX page to properly install the CUDA 11 or 12 version.
+3. (<i>Optional</i>; only for GPU version) Install JAX for either CUDA 12 , depending    on your system setup. Follow the    <a href="https://jax.readthedocs.io/en/latest/installation.html">installation instructions</a> on the official JAX page to properly install the CUDA 11 or 12 version.
 
-<!--
-3. (<i>Optional</i>) Install, a pre-package installation step (for only the
-   non-ngclearn dependencies), the base requirements (and a few extras for building
-   the docs) with:
-```console
-$ pip install -r requirements.txt
-```
--->
-
-3. Install the ngc-learn package via:
+4. Install the NGC-Learn package via:
 ```console
 $ pip install .
 ```
@@ -68,22 +44,21 @@ or, to install as an editable install for development, run:
 $ pip install -e .
 ```
 
-If the installation was successful, you should see the following if you test
-it against your Python interpreter, i.e., run the <code>$ python</code> command
-and complete the following sequence of steps as depicted in the screenshot below:<br>
-<!--<img src="images/test_ngclearn_install.png" width="512">-->
+If the installation was successful, you should see the following if you test it against your Python interpreter, i.e., run the <code>$ python</code> command and complete the following sequence of steps as depicted in the screenshot below:<br>
 
 ```console
 Python 3.11.4 (main, MONTH  DAY YEAR, TIME) [GCC XX.X.X] on linux
 Type "help", "copyright", "credits" or "license" for more information.
 >>> import ngclearn
 >>> ngclearn.__version__
-'2.0.3'
+'3.0.0'
 ```
 
+<!--
 <i>Note</i>: If you do not have a JSON configuration file in place (see tutorials
 for details) locally where you call the import to ngc-learn, a warning will pop
 up containing within it "<i>UserWarning: Missing file to preload modules from.</i>";
 this still means that ngc-learn installed successfully but you will need to
 point to a JSON configuration when building projects with ngc-learn.
+-->
 
diff --git a/docs/modeling/neurons.md b/docs/modeling/neurons.md
@@ -86,6 +86,22 @@ and `dmu` is the first derivative with respect to the mean parameter.
     :noindex:
 ```
 
+#### Bernoulli Error Cell
+
+This cell is (currently) fixed to be a (factorized) multivariate Bernoulli cell. 
+Concretely, this cell implements compartments/mechanics to facilitate Bernoulli 
+log likelihood error calculations. 
+
+```{eval-rst}
+.. autoclass:: ngclearn.components.BernoulliErrorCell
+  :noindex:
+
+  .. automethod:: advance_state
+    :noindex:
+  .. automethod:: reset
+    :noindex:
+```
+
 ## Spiking Neurons
 
 These neuronal cells exhibit dynamics that involve emission of discrete action
@@ -117,10 +133,42 @@ negative pressure on the membrane potential values at `t`).
     :noindex:
 ```
 
+### The IF (Integrate-and-Fire) Cell
+
+This cell (the simple "integrator") models dynamics over the voltage `v`. Note that `thr` is used as the membrane potential threshold and no adaptive threshold mechanics are implemented for this cell model. 
+(This cell is primarily a faster, convenience formulation that omits the leak element of the LIF.)
+
+```{eval-rst}
+.. autoclass:: ngclearn.components.IFCell
+  :noindex:
+
+  .. automethod:: advance_state
+    :noindex:
+  .. automethod:: reset
+    :noindex:
+```
+
+### The Winner-Take-All (WTAS) Cell
+
+This cell models dynamics over the voltage `v` as a simple instantaneous 
+softmax function of the electrical current input, where only a single 
+spike, which wins the competition across the group of neuronal units 
+within this component, emits a pulse/spike.  
+
+```{eval-rst}
+.. autoclass:: ngclearn.components.WTASCell
+  :noindex:
+
+  .. automethod:: advance_state
+    :noindex:
+  .. automethod:: reset
+    :noindex:
+```
+
 ### The LIF (Leaky Integrate-and-Fire) Cell
 
 This cell (the "leaky integrator") models dynamics over the voltage `v`
-and threshold shift `thrTheta` (a homeostatic variable). Note that `thr`
+and threshold shift `thr_theta` (a homeostatic variable). Note that `thr`
 is used as a baseline level for the membrane potential threshold while
 `thrTheta`  is treated as a form of short-term plasticity (full
 threshold is: `thr + thrTheta(t)`).

diff --git a/docs/modeling/synapses.md b/docs/modeling/synapses.md
@@ -1,17 +1,7 @@
 # Synapses
 
-The synapse is a key building block for connecting/wiring together the various
-component cells that one would use for characterizing a biomimetic neural system.
-These particular objects are meant to perform, per simulated time step, a
-specific type of transformation -- such as a linear transform or a 
-convolution -- utilizing their underlying synaptic parameters.
-Most times, a synaptic cable will be represented by a set of matrices (or filters) 
-that are used to conduct a projection of an input signal (a value presented to a
-pre-synaptic/input compartment) resulting in an output signal (a value that
-appears within one of its post-synaptic compartments). Notably, a synapse component is
-typically associated with a local plasticity rule, e.g., a Hebbian-type
-update, that either is triggered online, i.e., at some or all simulation time
-steps, or by integrating a differential equation, e.g., via eligibility traces.
+The synapse is a key building block for connecting/wiring together the various component cells that one would use for characterizing a biomimetic neural system. These particular objects are meant to perform, per simulated time step, a specific type of transformation -- such as a linear transform or a convolution -- utilizing their underlying synaptic parameters. Most times, a synaptic cable will be represented by a set of matrices (or filters) that are used to conduct a projection of an input signal (a value presented to a pre-synaptic/input compartment) resulting in an output signal (a value that appears within one of its post-synaptic compartments). There are three general groupings of synaptic components in ngc-learn: 1) non-plastic static synapses (only perform fixed transformations of input signals); 2) non-plastic dynamic synapses (perform time-varying, input-dependent transformations on input signals); and 3) plastic synapses that carry out long-term evolution. 
+Notably, plastic synapse components are typically associated with a local plasticity rule, e.g., a Hebbian-type update, that either is triggered online, i.e., at some or all simulation time steps, or by integrating a differential equation, e.g., via eligibility traces.
 
 ## Non-Plastic Synapse Types
 
@@ -74,6 +64,20 @@ This (chemical) synapse performs a linear transform of its input signals. Note t
     :noindex:
 ```
 
+### Double-Exponential Synapse
+
+This (chemical) synapse performs a linear transform of its input signals. Note that this synapse is "dynamic" in the sense that its efficacies are a function of their pre-synaptic inputs; there is no inherent form of long-term plasticity in this base implementation. Synaptic strength values can be viewed as being filtered/smoothened through a doubleexpoential / difference of two exponentials kernel.
+
+```{eval-rst}
+.. autoclass:: ngclearn.components.DoubleExpSynapse
+  :noindex:
+
+  .. automethod:: advance_state
+    :noindex:
+  .. automethod:: reset
+    :noindex:
+```
+
 ### Alpha Synapse
 
 This (chemical) synapse performs a linear transform of its input signals. Note that this synapse is "dynamic" in the sense that its efficacies are a function of their pre-synaptic inputs; there is no inherent form of long-term plasticity in this base implementation. Synaptic strength values can be viewed as being filtered/smoothened through a kernel that models more realistic rise and fall times of synaptic conductance..

diff --git a/docs/museum/event_stdp_patches.md b/docs/museum/event_stdp_patches.md
@@ -0,0 +1,13 @@
+# Event-based Spike-Timing-Dependent Plasticity (Tavanaei et al.; 2018)
+
+In this exhibit, we create, simulate, and visualize the internally acquired receptive fields of the spiking neural 
+network (SNN) trained via event-based spike-timing-dependent plasticity (EV-STDP) over image patches. This 
+reproduces the SNN model originally proposed in (Tavanaei et al., 2018) [1].
+
+The model code for this exhibit can be found 
+[here](https://github.com/NACLab/ngc-museum/tree/main/exhibits/evstdp_patches).
+
+<!-- references -->
+## References
+<b>[1]</b> Tavanaei, Amirhossein, Timothée Masquelier, and Anthony Maida. "Representation learning using event-based 
+STDP." Neural Networks 105 (2018): 294-303.