Alternative AI

Dynamic population encoders author: Tofara moyo The human brain is an amazing machine. It is composed of billions of neurons , exchanging information (and adapting the ways they exchange information) in order to learn and process information that the individual receives. We know that neurons have a binary , on or off nature, and it is in the pattern of neurons firing and not firing that consciousness emerges. We assume that population codes are the way that the brain chooses to represent concepts rather than other theories such as grandmother neurons. The population code theory is that concepts are represented in the brain by groups of firing neurons, rather than individual neurons , which if it was individual neurons, would imply the hypothesis that grandmother cells are the way the brain encodes information. What this means is when you think of the concept “cat”. Each time you think it roughly the same group of neurons will fire in a specific part of the brain. Also when you perceiv...

We have an algorithm that detects if someone has flue like symptoms is in the vicinity, just by the tone in his speech. We are not sure yet if we can accurately differentiate between Covid type flue like symptoms and those from another cause. Regardless it should be clear that the percentage of covid infected people is higher within the set of people with flu like symptoms than in the general public. So this should still serve useful. At its broadest then it protects the user from both flu and covid . This could be implemented in an android app that is constantly on on the smart phone, even in the users pocket. The moment it hears through the earpiece someone speak it will use adapted bio metric technology to check if they have flu like symptoms and set of an alarm or vibrate if they do. That gives you the chance to avoid close contact with the indicated person, and perhaps urge them to go for more thorough testing. This application can be used by the authorities to monitor everyone...

I have a neural netwok that takes in a random noise vector and maps it explicitly to an image. If i was to do this with one training example , it would memorize the example. if i increase the number of examples, it starts to unlearn the previous examples in order to learn the new ones. Think of the equation of a straight line. y = mx + c where y is the image, x is the random noise vector, m is the weight matrix and c is the bias term so with the first example we can change m the weight matrix, through training, till we fit x to y if we took another training pair we would need to change m again and so unlearn the first example. we will have to do it another way thsi will involve having two weight matrices. W and a soft copy of W called W2 W will b the template weight matrix. and W2 will be made by swapping around the indeces without affecting their memory allocation as this is a soft copy of W What this will mean is that on the graph we have a family of straight lines, whose gradie...

I would like to publish concepts concerning fMRI software to increase detection accuracy to give it a better temporl reolution as ell s a new type of imging technique We could have a neuron that leves a clear marker such as a magnetic pulse as soon as it fires as the basis of a new imaging technique..This would be done similar to the way the people at this site https://www.engadget.com/2018/05/10/ai-new-3d-model-predictive-human-cells-biology/?fbclid=IwAR1gLk5ANQBDT-h0rYqb3H2NovJEGfr0ianRqbu2hllhm56X9GcXZzIubHo edited the genes of cells to release phlourescent markers....also why would we not be able to have an fMRI based software that detects only up to a certain concentration of oxygen in an area ,also only when it occurs in an area that has the growth of the oxygen level that follows the pattern that the curve associated with that found in the build up to the neuron receiving a full supply of oxygen?

The axiom of identity states that For any "thing" (A = A) & (!A ! = A), which means that a thing is itself and not what its not. this is ubiquitous about nature and as we will see also expresses itself among the distribution of natural things as patterns. it is important for us in the field of AI because it introduces a complement to the hebbian factor which is that that things seemingly not related actually correlate. if A = A represents the hebbian factor (a thing is coincident with itself) then the other part would be !A != A (a thing is not coincident with what its not). But we see some more information than that last present in the complement. It fully contains all those elements found in A=A within its structure, i.e there are two A's in its expression as well as an equal sign. This should lead us to need to express it more appropriately as "a thing is coincident with those things that are not coincident with itself" . but that does not make full sens...

Imagine a tessellation made from equilateral triangle shaped tiles. We could add more and more tiles besides each other till we reach infinity. Now we would like to model the following properties of language using a tessellation. We want for different shapes of tiles to be fitted together in our tessellation, where different tiles contain different information in the form of sentences.This will be useful in a number of ways. The process of communication will be equivalent to selecting a particular tile from this space.So could the process of acquiring commands to give to an agent responsible for making actions. To select a tile we may choose to select an Nth term in this tessellation according to some sorting algorithm that sorts this space of tessellations. We will also depart from having these tiles tessellate a Euclidean space, but have it be a non-Euclidean manifold, in order for the shapes to fit as we would like. In our tessellation procedure, we may begin with one sentence and a...

If we could build a lens , where we sample from spaces itteratively in order to generate a particular, we may have a model that simplifies the process. And aids in keeping the selection process a series of linear transformations. For example, if we would like to generate an entire video, we could train an algorithm , perhaps with a VAE to selct the priinciple components of videos and then sample from this distribution. It will be up to the system to learn these components on its own, but the axes of this distribution are not objects in their own right. A point on a manifold is selected that is defined by the information it contains, which is a complete instance of a video. The system proposed described separates features and creates a manifold for each. Each new manifold will be linked by a parameter for selecting from that space. For this paper I present these manifolds as euclidean spaces that are positioned within a cascade. What this means is that , during the process of generation...

You can randomly set up a word vector for each word, but depending on chance some samples of random choices would work better than others, infact with the different input vectors , the loss landscape is altered...... as it is word vectors are not random....so we could imagine making them less random through the learning process by backpropagating a loss that takes in the inputs as variables, rather than the weights of the network...i believe that perhaps when we learn new information, the representations of the words (i.e. how they are understood) is altered fundamentally and the BNN then uses the exact same network to process these differing variables...so when we learn information relating "x is a y" the actual representation of the four words changes...along with a whole lot of other words (perhaps ALL words) in order to give you the disposition to talk about this relationship in different ways without having to train a new network. Eg. if "john is a star student...

The theory of form is the theory of complimentary inverses. Simply put if there is something bigger than something else, then there is something smaller than something else. In fact those two things exist as a function of each other. Existence itself relies on a thing not being equal to everything else (and so everything else is not equal to it). Given these insights, when given partial information on the state of a closed system we can populate it completely. The algorithm could generate the inverse of that found information in one go , or it would segment itself in a hierarchical manner revealing more and more detail and hence customising the information being generated in the empty space. The segmentation process basically focuses on proportion. We start off with a low resolution of the given information, this reveals a few large areas that are related. The system then groups similar regions according to the nature of the segments (in images this could be the general pixel values o...

I have an ambitious project where a musician can play a few chords , then the algorithm completes the whole song together with a music video for it. i will train my system on the billboard charts throughout the years and the artist has the option of stipulating which year he wants the song to sound like its from. First i create a tree that starts whith the whole song at the top node then branches of on and on till it reaches the bit stage. During training different songs will have different trees, but i will back propagate to the bit level an expected value of say 5. The back propagation will cause the tree to be set up in a particular way. So all songs in the training set will then be represented by a "type" of tree, though the trees will still be unique. Then during operation if you play a few chords the algorithm will set up that part of the tree for the song while at this stage the rest of it is random. finally we forward propagate through this partially random tree and g...

I have written a paper on a new type of network for NLP but i have lingering questions on how efficient and effective it is....this is a link to it on my blog... http://alternativeai.blogspot.com/2018/05/abstract-submited.html So the following is a more formal framing of efficiency and effectiveness in this network that i would appreciate input on. i have a type of network...it has one output node connected to all 4 hidden layer nodes, which are connected to the 12 input layer nodes the following  way.Each  is connected to exactly 9 nodes and the set of all sets of 3 nodes not being used by each node in the hidden layer consist of disjoint sets....this just means that we cant have any 2 nodes connected to the exact same nine nodes...or in general , we cant have any two nodes share missing nodes between them...... if this is clear so far there is another condition....the inputs of these input nodes is a number and each node in the hidden layer simply sums all the numbers from t...

BACKPROPAGATION ON A NOVEL NETWORK (NON ANN) FOR HATESPEECH DETECTION AND MORE This paper introduces a novel type of network that can accurately classify "hate speech" and differentiate it from normal content. It develops a network centered around a unique POS (part of speech) tagging type of system whose specifics are learnt by the network. Each word is assigned variables that indicate the polarity, (sign) of the effect a particular word has on every other word in a sentence, the magnitude of that polarity and also to what extent the word filters itself from the effect from other words. When choosing a set of properties, we would like to properly understand what we want the network to do. We know that both posts classified as hate speech and those not contain samples of words from a common pool (they share words). But we still want that the results for opposite classes to polarize. On top of this I believe that this represents a complex system, in that small chang...

This involves a "hate speech" or "spam" detection algorithm. (depending on the training data). This will be based on ANN theory , and involve the backpropagation algorithm while not based on an actual neural network. The training data will be labeled into two classes, "hate speech" and "non hate speech".   Hate speech will have an expected value of 1 , representing certain hate speech, while non hate speech will have an expected value of -1.   So what we would like is for the software to be input a post and gives it a value of 1 or -1, or something much closer to one or the other. During training The program will compute a value by performing the equivalent of forward propagation through the parameters we assign to each of multiple structures we will embed in the input ...then using this value and the epected value we will compute a cost function. We will then backpropagate through the heirachical structure of parameters in the direc...