Swudu Susuwu

Simple Python artificial neural networks/maps (FLOSS): https://github.com/CarsonScott/HSOM Lots of FLOSS neural network activation functions: https://github.com/Rober-t/apxr_run/blob/master/src/lib/functions.erl Lots of FLOSS neuroplasticity functions: https://github.com/Rober-t/apxr_run/blob/master/src/lib/plasticity.erl Lots of FLOSS neural network input aggregator functions: https://github.com/Rober-t/apxr_run/blob/master/src/agent_mgr/signal_aggregator.erl Simple to convert Erlang functions to Java/C++ to reuse for fast programs, the syntax is close to Lisp's No affiliations to authors

Github has lots of artificial neural networks unlicensed/FLOSS Q: "What brain regions do albatrosses have?" Q: "How do birds have so much more intelligence per neural volume versus humans?" Q: "How to base artificial neural networks off us birds to allow to lower resource use versus ones based off of human cortices?" Q: "Goose and albatross process lots per neural volume versus humans, because birds evolved from dinosaurs and so had longer to optimize neural structures versus mammals, howto base artificial neural networks off of goose or albatross neural networks?" Q: "Modern artificial neural networks such as Spinnaker are based off human neural networks because humans are the smartest of mammals, but lots of robots can not house enough RAM and CPUs, so as opposed to neuromorphic artificial neural networks based off on humans, how about based off of goose or albatross?" Versus humans

Human eyes use ganglion neurons to compress data from raw photons and output simple shapes/motions that go to V1 cortex. V1 cortex processes those and compresses to data as objects and motions of objects that go to V2 cortex. A few thousand neurons should allow to put compressed visual data to human's cortices https://www.linkedin.com/pulse/from-light-sight-part-i-photons-neural-signals-gabriel-a-silva https://link.springer.com/article/10.1007/s00424-007-0242-2 https://www.nature.com/articles/srep08344 https://www.scientificamerican.com/article/elon-musks-neuralink-has-implanted-its-first-chip-in-a-human-brain-whats-next/ https://en.wikipedia.org/wiki/Visual_cortex

Should allow AI human-form conscious: Spinnaker-class network of neurons (axons do human-neuron action potentials as opposed to 1-op or 2-op function that just adds inputs to form outputs,) + audio-processor region (multi layer, codes raw audio input to more compressed forms such as variations of tone, direction or loudnees, more layers up would code to syllables or objects, more layers up codes to words or audio-derived motions of objects around yoo) + vision-processor region (multi layer; low layers would code photons to variations of color or brightness, upper layers would code to geoooo info, such as structures or toolssss) + gustation-processor region (would code from chemical-sensors to info about compositions of molecules) + somatosensor-processor region (would code from hot-sensors/cold-sensors/pressure-sensors to geo info about structures, plus proprioception) + thamalus region to hookup sensors (such as howto position "up" based off of vision or proprioception, how to do location of structures from vision + audio + somatosensor) + hippocampus to form memories from sensors + neocortex region for pattern-recognition-0units to form long-term-memories and learn howto do work from unconscious playback from hippocampus + mirror neurons to form inputs to thalamus/hippocampus from new stuff those around you use tools for, to allow to figure out howto perform new labors or use new tools + default mode network for introspection (such as to lookup memories of emotions from hormones + memories of thoughts/ideas + memories of learned work + memories of how others do work or behaviours, to form new solutions) + a limbic system for hormones (such as hormones that alter how much of your processor to use to process what surrounds you now, or how much to use for introspection) + a human-form controlled from servos/motors, or simulator form that allows to move around a virtual world that allows human motions and has inputs for all sensors. Purposes/uses: allows autonomous robots to produce complex goods for us (Fanucs/Kukas/Facteons are limited to simple macros,) allows more good simulators to do decisions/solve problems for us, allows AI to form/run schools for us.

"How much energy would you put into ITER to fuse 1 kilogram of lead into gold?" ... to fuse 1 kilogram of lead (Pb) into gold (Au), we need to consider the mass difference between the two elements and the energy release per nucleon during fusion. The atomic mass of lead is approximately 207.2 atomic mass units (AMU), and the atomic mass of gold is around 197.0 AMU. Therefore, to convert 1 kilogram (1000 grams) of lead into gold, we need to account for the mass difference, which is 10.2 AMU. The energy release per nucleon during a fusion reaction is typically on the order of millions of electron volts (MeV). However, the exact value depends on the specific reaction and isotopes involved. For the sake of estimation, let's assume an energy release of 7 MeV per nucleon. To calculate the total energy required, we multiply the mass difference by the energy release per nucleon and the number of nucleons in 1 kilogram of lead. The number of nucleons can be estimated using Avogadro's number and the molar mass of lead. ... Number of nucleons in 1 kilogram of lead (Pb): (1000 g) / (207.2 g/mol) * (6.022 x 10^23 nucleons/mol) ≈ 2.91 x 10^26 nucleons Energy required: (10.2 AMU) * (7 MeV/AMU) * (2.91 x 10^26 nucleons) ≈ 2.03 x 10^28 MeV Converting MeV to joules: 1 MeV = 1.602 x 10^-13 joules Energy required (in joules): (2.03 x 10^28 MeV) * (1.602 x 10^-13 joules/MeV) ≈ 3.25 x 10^15 joules So, it would take approximately 3.25 x 10^15 joules of energy to fuse 1 kilogram of lead into gold. "Gold is not evenly divisible by helium, so you could not fuse helium into 100% pure gold, there would be other atoms formed, but if that is acceptable, how much helium to fuse to form 1 pound of gold, and how much joules would you lose (of course, past iron fusion loses joules, so this would not produce joules, just produce gold) to compress (through supermagnets, lasers, or other compressors) helium to gold?" To form 1 pound of gold through helium fusion, we need to determine the amount of helium required. Let's start by calculating the number of gold atoms present in 1 pound of gold. The molar mass of gold (Au) is approximately 197 grams/mol. Since 1 pound is equal to 453.592 grams, we can calculate the number of moles of gold: Number of moles of gold = (1 pound / 453.592 grams) * (1 mol / 197 grams) ≈ 0.002301 moles of gold In the fusion reaction, four helium nuclei (alpha particles) combine to form a nucleus of beryllium, and then another helium nuclei fuses with the beryllium nucleus to create a carbon nucleus. This carbon nucleus then captures three helium nuclei to produce an oxygen nucleus, and so on. It takes a series of fusion reactions to convert helium into gold. The exact number of helium nuclei required depends on the specific pathway and conditions of the fusion process. However, it is estimated that around 10^19 helium nuclei (or alpha particles) would be required to produce 1 gram of gold. Since there are approximately 453.592 grams in a pound, the total number of helium nuclei required would be: Number of helium nuclei = (10^19 helium nuclei / 1 gram) * (453.592 grams / 1 pound) ≈ 4.53592 × 10^21 helium

Calculus of how genes grow human organs: https://sc.edu/study/colleges_schools/artsandsciences/mathematics/our_people/directory/vasquez_paula.php https://www.sciencedirect.com/science/article/pii/S0898122109005343 https://www.engadget.com/2019-04-20-hitting-the-books-infinite-powers.html https://phys.org/news/2019-06-genes-interact-tissues.html https://openstax.org/books/concepts-biology/pages/18-2-development-and-organogenesis Calculus shows us how to produce retroviruses to ungrow vulva/phallus and grow phallus/vulva? Science shows us how the fetus blastocysts form endoderms, mesoderms and ectoderms which form all organs: https://training.seer.cancer.gov/disease/categories/tissues.html https://www.ncbi.nlm.nih.gov/books/NBK554394/ https://embryo.asu.edu/pages/mesoderm https://embryo.asu.edu/pages/endoderm https://embryo.asu.edu/pages/ectoderm Science shows us the full genome of humans, and thus, how the blastocysts form all human organs: https://hgdownload.soe.ucsc.edu/downloads.html https://www.ncbi.nlm.nih.gov/genome/guide/human/ Organs which ungrow include the adrenal glands and thymus glands, and muscle atrophy plus hair loss, but that's not organs. Just look up which genes ungrow those, and produce a retrovirus to have altered versions of those genes ungrow phallus/vulva, look up which genes grow vulva/phallus, and use to produce retrovirus to grow vulva/phallus? And to ungrow (or grow) mam glands?

Howto produce AIs that run close-to-conscious (do all human functions, just no proof of souls): Should allow AI human-form conscious: Spinnaker-class network of neurons (axons do human-neuron action potentials as opposed to 1-op or 2-op function that just adds inputs to form outputs,) + audio-processor region (multi layer, codes raw audio input to more compressed forms such as variations of tone, direction or loudnees, more layers up would code to syllables or objects, more layers up codes to words or audio-derived motions of objects around yoo) + vision-processor region (multi layer; low layers would code photons to variations of color or brightness, upper layers would code to geoooo info, such as structures or toolssss) + gustation-processor region (would code from chemical-sensors to info about compositions of molecules) + somatosensor-processor region (would code from hot-sensors/cold-sensors/pressure-sensors to geo info about structures, plus proprioception) + thamalus region to hookup sensors (such as howto position "up" based off of vision or proprioception, how to do location of structures from vision + audio + somatosensor) + hippocampus to form memories from sensors + neocortex region for pattern-recognition-0units to form long-term-memories and learn howto do work from unconscious playback from hippocampus + mirror neurons to form inputs to thalamus/hippocampus from new stuff those around you use tools for, to allow to figure out howto perform new labors or use new tools + default mode network for introspection (such as to lookup memories of emotions from hormones + memories of thoughts/ideas + memories of learned work + memories of how others do work or behaviours, to form new solutions) + a limbic system for hormones (such as hormones that alter how much of your processor to use to process what surrounds you now, or how much to use for introspection) + a human-form controlled from servos/motors, or simulator form that allows to move around a virtual world that allows human motions and has inputs for all sensors. Am not sure if this would have use for us, or if just calculus to program autonomous robos would do for us. This is more difficult to do, but such conscious would allow to solve red-tape problems for us beyond just how to program autonomous robos to produce for us. If this would do, what language to use? Produced computer-generated-simulations (from Sakura School and Bud) of how to run autonomous robos: The most I found of others' autonomous robos (mashup from lots of sources): Was the limit so-far just that most of those robos used to cost >$10,000 to produce? The robos from the mashup = Facteons, Kukas and Fanucs. Most use servos with outputs from 1kW to 10kwWs. The robos are formed just from: CPUs, hulls, transmissions and servos. Tons of 2ghz+ CPUs for <$10 from loads of sources. Iron or aluminum is affordable (for hulls of robos) to mass produce. Robos could mass-produce transmissions (Youtube has shows of robos that assemble own motors,) or you could use direct-drive servo motors. 4kw servos for $40 should allow you to form autonomous production. Should allow to produce for around $200 for us. Amazon is 1 source for those servos: https://www.amazon.com/ASMC-04B-Support-12V-24V-180kg-cm-Quadcopter/dp/B07GDJBDW9/ Robos mass-produce own motors: https://youtube.com/watch?v=bQ-YkFzWj6o

I have not saw an autonomous robot do work for us, just videos on Youtube that were possibly computer generated (of autonomous robots in factories.) Besides red tape problems that only politicians can solve, what problems to solve to have all goods (houses, vehicles, desktops, phones, foods) produced from autonomous robots for us? Howto program general purpose robos autonomous: Q: "Could you use bfs/dfs/iddfs to output codes for robos (such as Fanuc) to figure how to move servos to move the robos to perform a task or to produce for us, with the edges = servo motions and fitness function = desired outcome for us? Could you just have "max accelerate" and "max decelerate" of each servo as the graph node edges, and "product moved to desired position for us" (or "parts of product formed whole products for us") as fitness functions, and solve the "discrete" problem how you solve the problem that space is quantized (solution = calculus, or lots of small steps for us)? Plus restrict node edges that cause collisions, and compute load on servos so you don't overload the robos? If the search space is too large, could you use A-star with heuristics (such as "how close product is to desired location for us" or "how close parts have come to a formed product for us")? Could you use D-star for workplaces that have lots of other actors, for collision avoidance?" https://poe.com/chat/1yt9udz8p7mqvc9uwpl said: Yes, BFS/DFS/IDDFS, A-star, and D-star are all valid algorithms that can be utilized in the context of robotic motion planning and control. These algorithms can help generate code for controlling robots such as Fanuc to perform tasks and achieve desired outcomes. I apologize for the confusion in my previous responses. To clarify, here's how these algorithms can be applied: BFS/DFS/IDDFS: These algorithms can be used to explore the graph of possible servo motions, where the nodes represent servo positions and the edges represent servo motions or transitions. By defining a fitness function that represents the desired outcome, such as reaching a specific position or forming whole products, you can guide the search process towards finding a sequence of servo motions that maximizes the fitness function. Additionally, collision checking can be incorporated by restricting node edges that would cause collisions. To handle quantization or discrete servo positions, you can represent the search space as a discrete grid of positions. A-star: A-star is an informed search algorithm that can be used to find an optimal path in a graph by considering both the cost of reaching a node and an estimate of the remaining cost to the goal. In the context of robotic motion planning, A-star can be applied by defining appropriate heuristics that estimate the distance or effort required to achieve the desired outcome. For example, you can use heuristics such as the Euclidean distance between the current position and the goal position or the progress made towards forming a product. A-star can help efficiently explore the search space and find an optimal or near-optimal solution. D-star: D-star is a planning algorithm that can be used for dynamic replanning and collision avoidance in environments with changing conditions or obstacles. It maintains a map of the environment and updates the plan based on new information. In workplaces with multiple actors or changing obstacles, D-star can be used to dynamically adjust the robot's path to avoid collisions and achieve the desired outcome. In summary, these algorithms can be valuable tools for generating code and controlling robots to perform tasks. Should produce runnable code for those or someone else has? If should, what language to use? Java, C++, Python, or others?