wait, check sPlus / sMinus against the predicates. old s → new s → event check, names alone are not helping here archived model state: v , u , v0 , threshold state s and previous threshold state s_pre . neuronUpdates() runs with...
tiny neuron tests 🙂 easier to follow one trace than the whole network. check which declared state variables actually appear in the equation neuron-models/logistic_test.py: a single dimensionless neuron uses dv/dt = (0.1*v*(I-v))/tau , with...
sign from swapping the two event times, nice. draw pixels either side of a quantization boundary later; want to see how suddenly that pair moves Reference: base_model/mnistV1.py → temporal_switch(img, quant_levels=10) . The archived experiment...
interviews: ask about current problems BEFORE pitching HomeBuilt. “would use this” vs actually paying the pack price are very different answers, keep question versions + response exports two stages in the survey notes: pain-probing interviews...
scope / impact / niche / revenue... need a tiny test, not another giant idea list. Save rejected ideas w the assumption that killed them. otherwise I’ll rediscover the same thing in 3 months :) archive contents: an early idea brainstorm...
same 23→72.83 endpoints, two different percentage-gain claims in the posters. ugh recompute from the raw numbers; keep scoring definition + denominator nearby. percentage points and percent gain are not the same thing Engineering-plan targets...
poster recipe: 3 conv, 2 ReLU, flatten, 2 dense; lr 0.001 / 128 epochs / L2 missing widths, batch size, L2 coeff + exact loss path. save the checkpoint/log next to the diagram if found The poster supplies more concrete model details than the...
513 checks → 115, nice need runtime + input size too. fewer visited voxels doesn't automatically mean the same factor of speedup The tiny complexity sheet records exhaustive = 513 and tracing = 115 iterations. The ratio is 513/115 ≈ 4.46 ;...
reading pile: bottlenecks / false positives / FBC / phantom validation question to come back to — what ambiguity survives even when the synthetic example looks convincing? Saved readings worth keeping next to the implementation:...
pipeline versions: 20M vs 25M tracks, 0.06 vs 0.1 cutoff, TractSeg vs RecoBundlesX keep separate configs. subject/template transforms need to follow every output The Random Notes workflow starts with response estimation using Dhollander, a...
regression NOT classification — density / angle / position for matching in→out pieces what if several candidates want the same exit? also try tracing the bottleneck backward, should the pairings agree? The scratch note explicitly says...
Conv1D → BiGRU → more GRUs → norm → dense → sigmoid need layer sizes / sequence length alongside the nice boxes. also '3 states' but 4 names listed?? Poster architecture, transcribed in order: concatenated input → Conv1D →...
mean total 1.8844 s, but 21/50 trials over 2 s keep the tail, not just the average. battery trace gets to ~18 min continuous use... need duty-cycle notes next to that The latency sheet separates logic, mechanical and total response time across...
GRU sheets: 850 train / 150 test, no exact row overlap label 0 includes quick falls AND walking. need collection method + session split before treating that as a clean safe/unsafe dataset The three GRU spreadsheets are actual tabular data, not...
filename literally says SAMPLE confusion matrix, keep that attached fractional counts + June file vs September split sheets. not automatically the same experiment The document is explicitly named “JIC - sample confusion matrix.” Its two...
angle error / 2-minute drift / rate noise — three different things means under 5° but some readings over. also need to match each calibration number to its own run instead of borrowing the nicest one The CSEF angle-error table contains seven...
350 cm lever arm??? check whether that was meant to be 35 one digit and the COM shift grows a tentacle. redraw origin + actual weight positions before reusing this Board Stuff gives the one-dimensional relation x_COM = (m1*x1 + m2*x2)/(m1+m2) and...
10 lb each side: didn't turn. useful failure, keep it 5 lb averages look better than the slow individual trials. need load + starting angle + commanded rotation in the same row CSEF motor tests record that 10 lb on each side never turned in...
CookieDispenser.ino pin map here, actual code rather than guessing from the wiring picture btSerial on 5/6 is commented out; active status LED is pin 4. easy thing to miss Recovered the actual CookieDispenser.ino linked in the presentation,...
ID 1 = admin, 6 counters, next enrollment uses fingerCount+1 what stops ID 7 indexing past the array? also reboot + weekday reset need checking together The actual firmware allocates int numOfCookies[6] , int numOfTries[6] and int btWaitList[10]...
send '3' → count header + ba/bb/etc cookie events queue has 10 slots, append doesn't check capacity. if the reply gets lost, can refresh retry without counting the same cookie twice? The presentation links both the .ino and the MIT App Inventor...
