Google Tensor and CNN Programming is god aweful, 30 years behind

I had an interesting exchange on a Geoff Hinton video. To which, one person replied "Are you from the future?"

Sadly, the rediscovery of neural networks and the terrible models at stanford, Google's horrific tensor, and the generally terribly mathematical focus of OpenCL and CUDA (even RocM and AMDs instinct initiative) seem to think of NNs as matrix operations.

It's no wonder it seems like I'm from the future. Very frustrating that I will most likely have to write my own programming language to do what we want to do with Noonean Cybernetics.

---
I was doing a type of CNN called a Neural Cube in 1986 based on Fukishima's NeoCognitron work. Kunihiko Fukishima did much of the earliest work published in 1975 but his breakthrough was 1980 - http://www.cs.princeton.edu/courses/archive/spr08/cos598B/Readings/Fukushima1980.pdf "This network is given a nickname "neocognitron"l, because it is a further extention of the "cognitron", which also is a self-organizing multilayered neural network model proposed by the author before (Fukushima, 1975). Incidentally, the conventional cognitron also had an ability to recognize patterns, but its response was dependent upon the position of the stimulus patterns. That is, the same patterns which were presented at different positions were taken as different patterns by the conventional cognitron. In the neocognitron proposed here, however, the response of the network is little affected by the position of the stimulus patterns." I recommend my students start with that paper. My good friend Gerald Edelman, who sadly passed two years ago, led a huge amount of work on darwinistic CNNs through the 1980s and 1990s. He released Darwin III in 1988. Just to give you a sense of time. Karl Pribram's holonomic theory postulates that perception works like a hologram and that the dendritic processes function to take a "spectral" transformation of the "episodes of perception". This transformed "spectral" information is stored distributed over large numbers of neurons. When the episode is remembered, an inverse transformation occurs that is also a result of dendritic processes. It is the process of transformation that gives us conscious awareness. Pribram says that both time and spectral information are simultaneously stored in the brain. He also draws attention to a limit with which both spectral and time values can be concurrently determined in any measurement and this uncertainty describes a fundamental minimum defined by Gabor in 1946 (the inventor of the hologram) as a quantum of information. Working this into our neural model of perception and recognition is the leap that has occurred in the 30 years we stepped forward from the initial 1980s work. Every last commercial software, topology, tensorflow, all of that is absolute garbage. It's a bunch of junk. It's baby stuff. Useless except for googelian match the picture. CNN work has transitioned to evolving neural cube technology over 30 yrs since this early work. Hinton is a great thinker and I value his abstract thinking most. I wish he would move into theoretical concepts rather then demonstrate his old designs. When I saw his ted talk I was incredulous, dug out my thesis papers from 88 and there it was, the exact same stuff in a Hinton article. Restricted Boltzman machines are like seeing Edison's first prototype for an electric light bulb. Many of us were restrained because the computing power we needed to commercialize the tech in the 1980s was just out of reach. That's one part of what Noonean Cybernetics is helping solve, a 100 Teraflop desktop neural computer. With that there is no need to wait on university supercomputer resources in fact, we did an analysis of UofA's stampede doing neural work vs. one of ours and based on what you could actually reserve - their large array (and even then you had limited access to that much resource!), our computing on the desktop was actually more powerful than that massive system which cost 100 million dollars just to build the rooms and energy interconnects to install it into. Rather than spending 5 million dollars a year just on maintenance, The Noonean computer is just a personal computer. Embeddable low watt systems are still going to be 8 years off. But that is our direction. With holographic plane neural cube designs which have much more about excitation of pathways and dynamic re-organization than static CNNs, based on the work of Fukushima, Pribram, and Edelman, and our own original approach we are able to achieve much better recognition with much shorter training times. Minutes not days. Holographic neural frames train in a few minutes per feature. If you think about it, a hologram is much like Hinton's "capsules" as they are location equivariant. As I said. Take their google computer onto a busy street in NYC and show me where all the triangles are. They have a fundamentally broken approach. the hard stuff today is 3-d spatial awareness mapping, mapping recognition into long term memories, and conscious systems all integrated into language. And a fully unified system which does listening, speech, thought, vision, and interacts as a human would. That is our focus today. Another two decades away but we will have glimpses and early successes by 2025.

Koran details that the great pyramids were built by the Aad Giants

News appeared recently in a section of the media in India, Bangladesh and many other countries that a giant skeleton of enormous dimensions was excavated in some unknown desert. There was also a photograph of the skeleton with two investigators standing nearby. The skeleton's size can be judged from the height of the person standing near its skull. If calculated proportionately, the skeleton would be of a human having 60 to 80 feet height.

The first report appeared in the internet, telling that the skeleton was found somewhere in the deserts of western India. The Indian government had the area cordoned off by the Indian army and nobody was allowed to visit the site except a special National Geographic excavation team. For some unknown reason, all information about the discovery was kept secret. The report also mentioned about a stone tablet found along with the skeleton with ancient carvings in Sanskrit language on it. The inscription was deciphered and it revealed the secret of the skeleton. "In ancient times there lived giants who were called Rakshasas. They challenged divine orders and were eliminated for that."

The Indian mythology speaks about giants namely Rakshasas, who reigned over the forests. They ruled a country with the name Lanka and challenged the authority of the gods. In the Hindu epic Ramayana, Vishnu, the chief of the trio of supreme Hindu gods, incarnated in a royal family and killed the king of the Rakshasas. The report of the excavation of a skeleton of a Rakshasa was taken by some people as welcome proof for the reality of the Hindu mythological story. Without verifying the facts, the internet posting was further forwarded, spread widely and was taken very seriously by a large section of people.

A new version of the story appeared on 22 April 2004 in the Bangladesh newspaper The Nation. While reproducing the picture, a report by one Saalim Alvi from Riyadh told about a discovery in the south east of Saudi Arabia. In search of natural gas, a Saudi Aramco exploration team found a giant human skeleton in the desert. In the new version of the story, there is also a stone tablet, but the inscriptions are in Arabic language. They reveal that the skeleton is of a man of the ancient tribe Aad. The Aads were the descendants of the Quranic prophet Nooh (Noah in biblical mythology). They have been mighty giants, who were able to pull out big trees with one hand. The Aads were in charge of controlling the people of ancient times. But they challenged Allah's orders and were wiped out by him. The place where they lived is known as Rab-ul-Khaale, the empty place. The area where the skeleton had been discovered was overtaken by Saudi military, claimed the report in The Nation, and the picture was taken by a military helicopter.

the giants were referred to in the Koran as the "sons of Nooh (Noah)" which is quite interesting as I've never heard of Noah being referred to as very large in the bible. Apparently they were so big they could pull a fully grown tree out of the ground with one hand. The key point is that these giant myths were everywhere and 9' skeletons have been found and documented all across America. 

Congrats to Alli on hitting 100k

I was mentioned as a founder of Genetic Programming

Ha, I got mentioned in an article as a pioneer in Genetic Programming! cool! "While John Holland and his students were perfecting genetic algorithms, his colleagues (such as Nichael L. Cramer, John R. Koza and Gianna Giavelli) were founding the even more mind-boggling field of “genetic programming,” a similar evolutionary machine learning technique that can evolve and optimize a population consisting of entire computer programs designated to perform a task such as designing an electronic device, playing a game, predicting the movement of the stock market, etc." A Software That Evolves Itself Computers are becoming immensely powerful and the field of evolutionary computation is taken quite seriously. NEWSMAX.COM http://www.newsmax.com/RichardGrigonis/Education/2015/09/01/id/673072/

ActiveWeb (ActiveJDBC) and the Uber Lean Framework counter-revolution in Java

For years development frameworks have been constructed like a kitchen sink multi tool growing bigger and more bloated. PHP being barely object oriented is nothing but a list of 8000 functions. ICK! Even Java now has so many libraries and features that its a life effort to keep up.

Luckily, there is a answer. It's called JavaLite

JavaLite goes the other route. It doesn't even have sessions. It just barely got application scope. It doesn't manage HTTP get params.  It doesn't do much of anything really.

Or so it seems at first.

The main project is ActiveWeb. When I started using it a year ago its user guide was 20 pages.

It has a parallel project called Active JDBC. This is the bringer of magic.

Having suffered FIVE projects with endless pain updating and typing entities, and being horrified at database changes, ActiveJDBC is fully automatically generated behind the scenes and built into your compilation process. Hail JDBC.

The speed at which you can cobble together a ActiveWeb project is staggering.

LET me repeat that. STAGGERING

www.crossmypath.com is built entirely in activeweb. No JSF. No entity beans. No ugly php. Real code, readable, maintainable and a Model-View-Controller seperation that is much more clear than JavaJSF or Angular. (okok these aren't quite the same beasts I know)

I do think that this one man shop brilliance, by Igor Polevoy, does need a bit of a community process for next features, it does have support groups on google and elsewhere. It really would be a boon to have a built in user mgmt system with authentication and session scope storage. But other than that, its one heck of a ride to use this. It feels... like a summer breeze on a hot day.  Like a giant load of complexity we all thought was normal and needed is just... absent.

Kudos to JavaLite for doing the amazing. Like most great things, it was done by a single coder fed up with the crap. great job.

Suffering Spring - A patch that should have died wreaks havoc on software project

Spring came out when J2EE was in a bit of a mess. How it got into said mess is clear. Old CORBA shops wanting to have leverage in Java's direction pushed the design of J2EE into a world that it didn't need.

Soon you had local AND remote inferfaces, six files to configure just to get a simple entity out the door.

And the fact that Java was slow to support dependency injection. Which, is still a questionable technique that adds un-needed complexity and confusion to projects. Unless you really have dynamic type extensions over the life of the project or insane testing requirements, DI is a rats nest.

Take for example Springs wonderful implementation of @Service and @Repository and @Entity. Wow they finally support annotations. When you declare with @repository you get automatically exception translation back out to the invoker of the transaction. Sounds like a good idea. Until it gets confusing how the heck did this exception happen. No worries, you can control the translation via endless configuration files. Like the scene in brazil where deniro installs the patch to the air conditioning, its a maze of wires and pumping organs. ick.

Ah wait, it gets worse. Even with exception translation the calling method should receive what they translate to. Err no. Using a repository model the caller of the caller of the caller of the invocation is needed to trap exceptions. Aka yes, we had to set up THREE FASCADE calling layers to solve this. ARE YOU KIDDING ME!!!! And this is required if you really want to protect your code and log exceptions.

Anyways, J2EE was a mess. Spring stepped in. And for a while, it got customers. All hail spring.

But then, Java got its act in order. Cleaned up the interfaces. Cleaner simpler better. And Spring was trounced.

So after a year of trying to cobble Spring into a project, there were at least 5 times I had to stay until midnight and fix a mess that no one else could figure out. Security and password encryption are big messy areas in Spring. You would go down a path that SHOULD work, and it just wouldnt.

After losing about 5 years off my lifespan dealing with this non-sense, Lets officially announce - Spring is dead - except for loony psychos who like to play with fire. The community process and vetting is there for a reason in Java. It moderates out the chaos and eventually dumps bad design. In Spring, there is nothing.

Oh yah, and now java has simple clean dependency injection. There is simply no reason to lock into a single vendor anymore.  With java we have the different app server platforms, even different JDK versions.  And Oracle is ensuring quality. This is not just bias.

Will I ever do another Spring project? Uh, there aint enough gold in the Universe.

Book number TEN - The Rains

The rains is a teen story but suitable for adults who want a light read, on an adventure of a chubby boy who faces discrimination and ends up saving a town and uniting all the animal kingdoms. Its a bit wisdom-y and filled with some buddhist lessons for all of us on honor, friendship, and trust.