A Tsetlin machine is an Artificial Intelligence algorithm based on propositional logic.
Background
A Tsetlin machine is a form of learning automaton based upon algorithms from reinforcement learning to learn expressions from propositional logic. Ole-Christoffer Granmo gave the method its name after Michael Lvovitch Tsetlin and his Tsetlin automata. The method uses computationally simpler and more efficient primitives compared to more ordinary artificial neural networks.
As of April 2018 it has shown promising results on a number of test sets.
Types
Original Tsetlin machine
Convolutional Tsetlin machine
Regression Tsetlin machine
Relational Tsetlin machine
Weighted Tsetlin machine
Arbitrarily deterministic Tsetlin machine
Parallel asynchronous Tsetlin machine
Coalesced multi-output Tsetlin machine
Tsetlin machine for contextual bandit problems
Tsetlin machine autoencoder
Tsetlin machine composites: plug-and-play collaboration between specialized Tsetlin machines
Applications
Keyword spotting
Aspect-based sentiment analysis
Word-sense disambiguation
Novelty detection
Intrusion detection
Semantic relation analysis
Image analysis
Text categorization
Fake news detection
Game playing
Batteryless sensing
Recommendation systems
Word embedding
ECG analysis
Edge computing
Bayesian network learning
Original Tsetlin machine
Tsetlin automaton
The Tsetlin automaton is the fundamental learning unit of the Tsetlin machine. It tackles the multi-armed bandit problem, learning the optimal action in an environment from penalties and rewards. Computationally, it can be seen as a finite-state machine (FSM) that changes its states based on the inputs. The FSM will generate its outputs based on the current states. A quintuple describes a two-action Tsetlin automaton:
A Tsetlin automaton has states, here :
The FSM can be triggered by two input events
The rules of state migration of the FSM are stated as
It includes two output actions
Which can be generated by the algorithm
Boolean input
A basic Tsetlin machine takes a vector of Boolean features as input, to be classified into one of two classes, or . Together with their negated counterparts, , the features form a literal set .
Clause computing module
A Tsetlin machine pattern is formulated as a conjunctive clause , formed by ANDing a subset of the literal set:
.
For example, the clause consists of the literals and outputs iff and .
Summation and thresholding module
The number of clauses employed is a user-configurable parameter . Half of the clauses are assigned positive polarity. The other half is assigned negative polarity. The clause outputs, in turn, are combined into a classification decision through summation and thresholding using the unit step function :
In other words, classification is based on a majority vote, with the positive clauses voting for and the negative for . The classifier
,
for instance, captures the XOR-relation.
Feedback module
Type I feedback
Type II feedback
Resource allocation
Resource allocation dynamics ensure that clauses distribute themselves across the frequent patterns, rather than missing some and overconcentrating on others. That is, for any input , the probability of reinforcing a clause gradually drops to zero as the clause output sum
approaches a user-set target for ( for ).
If a clause is not reinforced, it does not give feedback to its Tsetlin automata, and these are thus left unchanged. In the extreme, when the voting sum equals or exceeds the target (the Tsetlin Machine has successfully recognized the input ), no clauses are reinforced. Accordingly, they are free to learn new patterns, naturally balancing the pattern representation resources.
Implementations
Software
Tsetlin Machine in C, Python, multithreaded Python, CUDA
Convolutional Tsetlin Machine
Weighted Tsetlin Machine in C++
Hardware
One of the first FPGA-based hardware implementation of the Tsetlin Machine on the Iris dataset was developed by the µSystems (microSystems) Research Group at Newcastle University. They also presented the first ASIC implementation of the Tsetlin Machine focusing on energy frugality, claiming it could deliver 10 trillion operation per Joule. The ASIC design had demoed on DATA2020.