GENERATION GENERATION


Te variation of individual organisms is key to the process of natural selection—if all things were the same, there would be no evolution—but these differences can be hard to distill into a single model that represents all objects in a particular class—i.e., all potatoes, or all anti-tank mines. Generative AI can be used to simulate variation, broadening the perspective on what a potato can be—in terms of how it looks or, in this case, how it feels.


One of the challenges in training image recognition models is that there can be infinite ways an object looks in the context of its environment. It might be seen from various angles, or partially hidden behind other objects. Anticipating all of these variations is impossible and finding representative images laborious. Gener- ative AI, however, allows us to expand on a smaller data set, introducing further variation to make the resulting model more robust—more accurate at identifying the target under varied circumstances—because it can better identify which features are significant in determining whether or not an object belongs in a particular class of objects. In other words, if we know what an anti-tank mine looks like partially buried, we (or our sensors) can identify them more accurately.


GENERATIVE DESIGN For more than a century, we’ve used a process called “design of experiments” or “experimental design” to determine the factors that contribute to performance of a process or design. Experi- mental design varies certain features in a design, the predictor variables, to gauge their impact on one or more response vari- ables—for example, how the length and width of a plane’s wings affect fuel usage. However, because there may be several predictor variables (length, width, etc.), and each of those may have many potential settings (12 meters, 13 meters, etc.), running a design of experiments can be complex and costly.


However, two factors have changed this paradigm in recent years. Te first is that advances in simulation allow digital engineer- ing models to be assessed without building physical components. Te second, more recent, factor is that computers can be used to rapidly generate and assess models, allowing a design of experi- ments to consider far more predictor variables and factors than previously possible. For the Army, we can apply this process to things like developing hardware chassis that optimize heat disper- sion, or a program that identifies command post configurations that reduce concentration of the radio frequency signature.


ADDITIONAL TRAINING


Generative design can be used for more than hardware—for example, course of action development, which Maj. Patrick Beaudry, a science and technology analyst for the Mission


30 Army AL&T Magazine Spring 2023


Generative pre-trained models are surprisingly accurate, but Army operations may need post-training of the models for more accurate responses. (Image generated by DALL-E 2)


SNAKE IN THE GRASS


Generative AI expands on smaller data sets, introducing further variation to make the resulting model more robust and accurate— such as different angles of a P1ZAM munition obscured by grass. (Image generated by DALL-E 2)


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96  |  Page 97  |  Page 98  |  Page 99  |  Page 100  |  Page 101  |  Page 102  |  Page 103  |  Page 104  |  Page 105  |  Page 106  |  Page 107  |  Page 108  |  Page 109  |  Page 110  |  Page 111  |  Page 112  |  Page 113  |  Page 114  |  Page 115  |  Page 116  |  Page 117  |  Page 118  |  Page 119  |  Page 120  |  Page 121  |  Page 122  |  Page 123  |  Page 124  |  Page 125  |  Page 126  |  Page 127  |  Page 128  |  Page 129  |  Page 130  |  Page 131  |  Page 132