{"id":84,"date":"2026-07-26T16:11:01","date_gmt":"2026-07-26T16:11:01","guid":{"rendered":"https:\/\/vexel.codes\/?p=84"},"modified":"2026-08-04T16:35:25","modified_gmt":"2026-08-04T16:35:25","slug":"current-design-thoughts","status":"publish","type":"post","link":"https:\/\/vexel.codes\/?p=84","title":{"rendered":"Current design thoughts"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">1. Initial goals and expectations &#8211; a self-interacting computational field:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Fractal-like and harmonic organization emerges from bulk interaction rather than from computation within individual units.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">2. Core Data Layer &#8211; The Sigmoid LUT (TANH to be considered separately):<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">At the foundation sits a highly optimized <strong>256-entry lookup table (LUT)<\/strong> generated via a classic logistic sigmoid function mapped across a strict domain from <strong>-6.0 to 6.0<\/strong>.  The table itself becomes an instantaneous index function, while filtering the input layer through the math.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Model Symmetry<\/strong>: The table leverages the symmetry of the logistic function around its midpoint.<\/li>\n\n\n\n<li><strong>Fixed-Point Scaling<\/strong>: Continuous values are crushed into discrete 16-bit unsigned integers (<code>uint16_t<\/code>) scaled up to <code>65535<\/code>.<\/li>\n\n\n\n<li><strong>Soft Crossover Dynamics:<\/strong> Mapping the normalized input range from \u22126 to +6 across 256 discrete entries produces a gentle, viscous gradient through the crossover region. Near the midpoint, the maximum change between adjacent entries is approximately 1.2% of the full output range, or about 2.4% relative to the local output value, providing a smooth transition within digital constraints.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">3. Information Compression &#8211; The 2-Bit State Machine:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">To avoid burning processing power on heavy floating-point numbers or handling complex noise, this system compresses activating inputs down into a crisp, <strong>2-bit primary output state<\/strong>. This functions as a localized information filter with four precise operational phases:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><code>00<\/code> \u2014 <strong>Inactive<\/strong>: The unit is completely dormant. The global engine can safely skip heavy processing of these nodes, short-circuiting computational waste.<\/li>\n\n\n\n<li><code>01<\/code> \u2014 <strong>Approaching Inactive<\/strong>: The signal is decaying. The system acts as a resistance buffer by slightly raising its activation threshold to prevent the unit from fluttering chaotically due to minor noise.<\/li>\n\n\n\n<li><code>10<\/code> \u2014 <strong>Approaching Active<\/strong>: The unit is priming itself by slightly lowering its threshold, indicating a rapid buildup of localized energy or density.<\/li>\n\n\n\n<li><code>11<\/code> \u2014 <strong>Active<\/strong>: Full execution\/firing state.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">4. Dynamic Feedback Loops &#8211; Shifting Thresholds:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The 2-bit state history feeds directly back into the input processing logic, giving each unit an organic sense of memory, fatigue, and physical readiness without needing global network weight adjustments:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>The Refractory Period (after state <code>11<\/code>)<\/strong>: Once a unit fires, it enters a high-threshold fatigue state. The system applies a sharp <strong>positive offset<\/strong> to the local threshold, making it much harder to fire again immediately and enforcing a natural wave decay.<\/li>\n\n\n\n<li><strong>The Priming State (<code>10<\/code>)<\/strong>: As a unit approaches activation, its local threshold is subtly <strong>lowered<\/strong>. This sensitizes the unit, making it more responsive to incoming activity and allowing clustered regions to fire cleanly together.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">5. Extended Field Mechanics &#8211; Phase and Rotation:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">To transition from a simple cellular automaton into a complex wave-resonance field, secondary, finer-grained states add to the primary 2-bit state:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Phase Alignment<\/strong>: Units evaluate whether they are in or out of phase with their neighbors. Matching phases constructively interfere to accelerate threshold crossings, while mismatched phases damp the signal.<\/li>\n\n\n\n<li><strong>Rotational Vectors<\/strong>: This introduces directional momentum and spatial coherence. Activation waves can spin, warp, and propagate with structural bias across the computational field<\/li>\n\n\n\n<li><strong>Computational Economy<\/strong>: The engine only pays the heavy processing cost for computing these continuous phase-shifts and rotational updates <em>after<\/em> a unit&#8217;s cheap 2-bit state passes its threshold validation.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">6.  Threshold decay function &#8211; Follow the field:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The threshold value itself should follow an R\/C like decay curve toward its normal resting, non-zero value &#8211; absent new activation, likely also involving a lookup table: Tt+1\u200b=T_rest\u200b+(Tt\u200b\u2212T_rest\u200b)e\u2212\u0394t\/\u03c4.  T_rest can be further modified by a slower historical function, but cannot be zero.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>1. Initial goals and expectations &#8211; a self-interacting computational field: Fractal-like and harmonic organization emerges from bulk interaction rather than from computation within individual units. 2. Core Data Layer &#8211; The Sigmoid LUT (TANH to be considered separately): At the foundation sits a highly optimized 256-entry lookup table (LUT) generated via a classic logistic sigmoid [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-84","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/posts\/84","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/vexel.codes\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=84"}],"version-history":[{"count":28,"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/posts\/84\/revisions"}],"predecessor-version":[{"id":145,"href":"https:\/\/vexel.codes\/index.php?rest_route=\/wp\/v2\/posts\/84\/revisions\/145"}],"wp:attachment":[{"href":"https:\/\/vexel.codes\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=84"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/vexel.codes\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=84"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/vexel.codes\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=84"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}