Black Tree AutoML
Humanity’s Fastest Deep Learning Software
Black Tree’s Runtimes and Accuracies are Unrivaled
Black Tree brings the power of parallel computing, together with data compression, producing runtimes that are simply incomparable to other Deep Learning techniques. For a high-level academic summary of the underlying algorithms, see “Vectorized Deep Learning“.
The results below were generated using Black Tree’s “Supervised Delta Classification” algorithm. This algorithm is included in the Free Version of Black Tree, so you can download the datasets below and see for yourself, that there is simply no contest between Black Tree and other Deep Learning techniques. Black Tree Massive includes a mathematically identical version of Supervised Delta Classification that makes better use of memory, and so accuracy is the same, despite superior runtimes. As a general matter, Black Tree Massive is typically significantly faster than Black Tree Pro, and some algorithms are several orders of magnitude faster. Datasets listed below were broken into random training / testing subsets, so accuracies can vary. All runtimes are in seconds, running on an iMac 3.2 GHz Core i5.
There is very little professional data online about the actual runtimes of Neural Networks (as opposed to their theoretical complexities), but all available data suggests that even running on GPUs and other truly parallel architectures, classifying even the smaller datasets below could take hours. This is consistent with a refereed article published by Elsevier, “Complexity Analysis of Multilayer Perceptron Neural Network Embedded into a Wireless Sensor Network“, that lists runtimes for some of the datasets below, including the UCI Iris Dataset, which a Neural Network took well over one hour to solve. This is simply not practical for certain business settings, where fast and reliable answers are required. The Free Version of Black Tree solves this classification task automatically (i.e., without a specialized model, using a single generalized algorithm) in 0.237 seconds, with 95.65% accuracy.
|Dataset||Classification Accuracy||Total Runtime (Pro)||Total Runtime (Massive)|
25,500 Training Rows
4,500 Testing Rows
|83.33%||1,467 seconds||223.7 seconds|
298 Training Rows
53 Testing Rows
|94.11%||0.755 seconds||0.201 seconds|
127 Training Rows
23 Testing Rows
|95.65%||0.237 seconds||0.086 seconds|
165 Training Rows
30 Testing Rows
|90.90%||0.379 seconds||0.083 seconds|
176 Training Rows
32 Testing Rows
|95.65%||0.513 seconds||0.108 seconds|
151 Training Rows
27 Testing Rows
|96.70%||0.310 seconds||0.082 seconds|
Black Tree’s image compression algorithms allow Image Classification tasks, including medical imaging classification, to be accomplished in roughly the same amount of time as Data Classification tasks, again producing simply unparalleled runtimes. Black Tree Pro and Black Tree Massive use the exact same image processing and classification algorithms. The Free Version of Black Tree includes the exact same algorithms, with a hard limit of 2,500 images.
The image on the left is a brain MRI (courtesy of Kaggle) that was compressed in .00191 seconds into the super-pixel image in the center, part of a process that classified 282 Testing Images over 1,597 Training Images (specifically, tumor classification) in 50.44 seconds (running on a MacBook Air), with 100% accuracy, using Black Tree Pro. The image on the right is automatically generated by all versions of Black Tree (including the Free Version), that shows the distribution of values by dimension for the largest cluster in the dataset, which is intended to provide a visual intuition for the distribution of values in the dataset. Accuracies and runtimes for the MNIST Numerical and MNIST Fashion Datasets are 99.95% and 286.09 seconds (5,000 Training Rows and 5,000 Testing Rows), and 92.85% and 15.90 seconds (1,000 Training Rows and 1,000 Testing Rows), respectively.
Black Tree Runs in a GUI
The front-end for Black Tree runs in an easy-to-use interface, reducing Deep Learning to a task that can be accomplished by an admin or assistant, thereby allowing for radical reductions to costs and headcount associated with Deep Learning. For the same reasons, Black Tree allows firms and individuals to spend a small sum of money (see pricing below) to test the question of whether investing in Deep Learning is worthwhile. For some users, this question can likely be answered by the Free Version of Black Tree.
Download the Free Version of Black Tree, which includes (i) data classification and clustering, and (ii) image classification (grayscale only), up to exactly 2,500 rows / images (non-commercial license), or select from the commercial licenses below.
NOTICE: All sales are final, no refunds available. For technical support, see Contact Information.
A lifetime commercial license for one user, which includes (i) data classification and clustering, and (ii) image classification and clustering (grayscale only), up to around 25,000 rows.
A lifetime commercial license for one user, which includes (i) all of the algorithms included in Black Tree Pro, (ii) a significantly faster Supervised Delta Classification algorithm, (iii) a significantly faster normalization algorithm, together with (iv) Massive Algorithms that can classify 500,000 rows in approximately ten minutes, and (v) confidence metrics that allow for precise classification.
Black Tree Osmium (Coming Soon for $99,000)
A lifetime commercial license for one user, which includes (i) preprocessing, compression, analysis, and anomaly detection algorithms that can be applied to data, image, video, and 3D and higher dimensional data and video (i.e., high-dimensional time-series), (ii) image and video classification algorithms, (iii) 3D object detection, tracking, and classification algorithms, (iv) high-dimensional time-series prediction and interpolation, (v) algorithms that can detect periodicity and stable average values in time-series data. All classification tasks can make use of both Pro and Massive Algorithms. (vi) N-Dimensional optimization.
Follow Black Tree on LinkedIn
For updates on new releases and academic papers